Vulnerability-Lookup

CVE-2026-73560 (GCVE-0-2026-73560)

Vulnerability from cvelistv5 – Published: 2026-08-17 20:17 – Updated: 2026-08-18 16:00

Title

vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

Summary

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mimo_v2_omni.py passes attacker-controlled image and audio strings through _fetch_image, requests.get, and Image.open instead of MediaConnector, bypassing allowed_media_domains and allowed_local_media_path protections and allowing server-side requests and reads of arbitrary files accessible to the vLLM process. This issue is fixed in version 0.26.0.

Severity

6.5 (Medium)


                        
                          CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

SSVC

Exploitation: poc Automatable: no Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-08-18 16:00 UTC

CWE

CWE-918 - Server-Side Request Forgery (SSRF)

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7637 records in the last 180 days details

References

4 references

URL	Tags
https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
https://github.com/vllm-project/vllm/pull/43117	x_refsource_MISC
https://github.com/vllm-project/vllm/commit/54503…	x_refsource_MISC
https://github.com/vllm-project/vllm/releases/tag…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version	CPE status
vllm-project	vllm	Affected: < 0.26.0	guessed

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-73560",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-18T16:00:28.999546Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-18T16:00:35.302Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.26.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mimo_v2_omni.py passes attacker-controlled image and audio strings through _fetch_image, requests.get, and Image.open instead of MediaConnector, bypassing allowed_media_domains and allowed_local_media_path protections and allowing server-side requests and reads of arbitrary files accessible to the vLLM process. This issue is fixed in version 0.26.0."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 6.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "NONE",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-918",
              "description": "CWE-918: Server-Side Request Forgery (SSRF)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-17T20:17:25.769Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/43117",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/43117"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5"
        },
        {
          "name": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0"
        }
      ],
      "source": {
        "advisory": "GHSA-4hhp-h66f-j5j7",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-73560",
    "datePublished": "2026-08-17T20:17:25.769Z",
    "dateReserved": "2026-08-12T20:53:46.380Z",
    "dateUpdated": "2026-08-18T16:00:35.302Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-73560",
      "date": "2026-10-14",
      "epss": "0.00407",
      "percentile": "0.33359"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "vllm",
                "vendor": "vllm-project",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 0.26.0"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "configurations": [
          {
            "nodes": [
              {
                "cpeMatch": [
                  {
                    "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                    "matchCriteriaId": "BB265B9E-EBAE-4833-8C3E-B203C8E9EC86",
                    "versionEndExcluding": "0.26.0",
                    "vulnerable": true
                  }
                ],
                "negate": false,
                "operator": "OR"
              }
            ]
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mimo_v2_omni.py passes attacker-controlled image and audio strings through _fetch_image, requests.get, and Image.open instead of MediaConnector, bypassing allowed_media_domains and allowed_local_media_path protections and allowing server-side requests and reads of arbitrary files accessible to the vLLM process. This issue is fixed in version 0.26.0."
          }
        ],
        "id": "CVE-2026-73560",
        "lastModified": "2026-09-28T18:41:05.437",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
                "version": "3.1"
              },
              "exploitabilityScore": 2.8,
              "impactScore": 3.6,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-73560",
                "options": [
                  {
                    "exploitation": "poc"
                  },
                  {
                    "automatable": "no"
                  },
                  {
                    "technicalImpact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-18T16:00:28.999546Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-08-17T21:16:48.960",
        "references": [
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Patch"
            ],
            "url": "https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Issue Tracking",
              "Patch"
            ],
            "url": "https://github.com/vllm-project/vllm/pull/43117"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Release Notes"
            ],
            "url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Mitigation",
              "Vendor Advisory"
            ],
            "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7"
          },
          {
            "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
            "tags": [
              "Mitigation",
              "Vendor Advisory"
            ],
            "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Analyzed",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-918"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "redhat_vex": {
      "aggregate_severity": "Moderate",
      "current_release_date": "2026-10-14T02:34:03+00:00",
      "cve": "CVE-2026-73560",
      "id": "CVE-2026-73560",
      "initial_release_date": "2026-08-17T20:17:25.769000+00:00",
      "product_status:fixed": "8",
      "product_status:known_affected": "22",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "vllm: vLLM: Server-Side Request Forgery and arbitrary file read via improper media processing",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-73560.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-73560",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-08-18T16:00:28.999546Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-08-18T16:00:12.424Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.26.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mimo_v2_omni.py passes attacker-controlled image and audio strings through _fetch_image, requests.get, and Image.open instead of MediaConnector, bypassing allowed_media_domains and allowed_local_media_path protections and allowing server-side requests and reads of arbitrary files accessible to the vLLM process. This issue is fixed in version 0.26.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 6.5,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "NONE",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-918",
                  "description": "CWE-918: Server-Side Request Forgery (SSRF)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-08-17T20:17:25.769Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/43117",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/43117"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0"
            }
          ],
          "source": {
            "advisory": "GHSA-4hhp-h66f-j5j7",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-73560",
        "datePublished": "2026-08-17T20:17:25.769Z",
        "dateReserved": "2026-08-12T20:53:46.380Z",
        "dateUpdated": "2026-08-18T16:00:35.302Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-73560

Vulnerability from fkie_nvd - Published: 2026-08-17 21:16 - Updated: 2026-09-28 18:41

Severity

6.5 (Medium) - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

Summary

References

URL	Tags
security-advisories@github.com	https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5	Patch
security-advisories@github.com	https://github.com/vllm-project/vllm/pull/43117	Issue Tracking, Patch
security-advisories@github.com	https://github.com/vllm-project/vllm/releases/tag/v0.26.0	Release Notes
security-advisories@github.com	https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7	Mitigation, Vendor Advisory
134c704f-9b21-4f2e-91b3-4a467353bcc0	https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7	Mitigation, Vendor Advisory

Impacted products

	Vendor	Product	Version
	vllm	vllm	*

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.26.0"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "BB265B9E-EBAE-4833-8C3E-B203C8E9EC86",
              "versionEndExcluding": "0.26.0",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mimo_v2_omni.py passes attacker-controlled image and audio strings through _fetch_image, requests.get, and Image.open instead of MediaConnector, bypassing allowed_media_domains and allowed_local_media_path protections and allowing server-side requests and reads of arbitrary files accessible to the vLLM process. This issue is fixed in version 0.26.0."
    }
  ],
  "id": "CVE-2026-73560",
  "lastModified": "2026-09-28T18:41:05.437",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "NONE",
          "baseScore": 6.5,
          "baseSeverity": "MEDIUM",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "NONE",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
          "version": "3.1"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 3.6,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-73560",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-08-18T16:00:28.999546Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-08-17T21:16:48.960",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Issue Tracking",
        "Patch"
      ],
      "url": "https://github.com/vllm-project/vllm/pull/43117"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Release Notes"
      ],
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Mitigation",
        "Vendor Advisory"
      ],
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7"
    },
    {
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "tags": [
        "Mitigation",
        "Vendor Advisory"
      ],
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-918"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-4HHP-H66F-J5J7

Vulnerability from github – Published: 2026-09-08 20:42 – Updated: 2026-09-08 20:42

Summary

vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

Details

Summary

vllm/transformers_utils/processors/mimo_v2_omni.py — the multimodal processor for MiMoV2OmniForCausalLM — issues requests.get(...) directly on user-supplied image and audio URL strings and Image.open(...) on user-supplied local paths, without the SSRF / allowed_local_media_path checks that vllm.multimodal.utils.MediaConnector was hardened with in GHSA-qh4c-xf7m-gxfc, GHSA-v359-jj2v-j536, and GHSA-pf3h-qjgv-vcpr.

This is the same bug class as those three published advisories, in a code path the patches missed. When a user passes a URL or local-file string through multi_modal_data (e.g. LLM.generate(multi_modal_data={"image": "http://..."})), the processor takes the unsanitized string and dispatches it without any URL-scheme allowlist, network-target allowlist, size cap, or local-path allowlist.

Details

File: vllm/transformers_utils/processors/mimo_v2_omni.py (current main)

Sink 1 — image SSRF + local-file read (_fetch_image, lines 231–249):

def _fetch_image(src: Any) -> Image.Image:
    if isinstance(src, Image.Image):
        return _to_rgb(src)
    if isinstance(src, bytes):
        return _to_rgb(copy.deepcopy(Image.open(BytesIO(src))))
    if isinstance(src, str):
        if src.startswith(("http://", "https://")):
            r = requests.get(src, timeout=30)              # SSRF: no allowlist, follows redirects
            r.raise_for_status()
            return _to_rgb(copy.deepcopy(Image.open(BytesIO(r.content))))
        if src.startswith("file://"):
            return _to_rgb(Image.open(src[7:]))            # arbitrary local file read
        if src.startswith("data:image"):
            ...
        return _to_rgb(Image.open(src))                    # fallback also opens local files
    raise ValueError(f"Unrecognized image source: {type(src)}")

Sink 2 — audio SSRF (around line 471):

elif audio.startswith(("http://", "https://")):
    r = requests.get(audio, timeout=30)                    # SSRF: same pattern
    r.raise_for_status()
    file_obj = io.BytesIO(r.content)

Reachability. _fetch_image is invoked from MiMoVLProcessor.process_image:

def process_image(self, image: ImageInput) -> torch.Tensor:
    kw = self._resolve_img_kw(image)
    src = image.image
    if isinstance(src, (str, bytes)):
        src = _fetch_image(src)
    ...

MiMoVLProcessor is wrapped by MiMoV2OmniMultiModalProcessor and registered for the MiMoV2OmniForCausalLM model architecture (vllm/model_executor/models/mimo_v2_omni.py:1169). Whenever a user passes a string into multi_modal_data["image"] (or ["audio"]) for this model, the unsanitized URL/path reaches the sink.

Comparison to the recent fixes. The remediation pattern adopted in the three earlier advisories was to route every external resource fetch through MediaConnector, which checks allowed_local_media_path and applies SSRF protection before issuing the network request. chat_utils.py (lines 838, 902, 924, 963, 1053, 1081) already uses self._connector.fetch_image / fetch_audio / fetch_video. The model processor in mimo_v2_omni.py was added later and skipped the connector — it calls requests.get and Image.open directly. Result: the public OpenAI chat-completion path is protected, but library use (LLM.generate(multi_modal_data=...)), batch processing, and any other path that lets a string reach the processor receive no protection.

Impact

SSRF — internal-network probing / cloud-metadata theft. Standard requests.get follows redirects and accepts any URL. An attacker who controls a multi_modal_data value can:
read AWS / GCP / Azure instance metadata (e.g. http://169.254.169.254/latest/meta-data/iam/security-credentials/),
probe internal services on the vLLM host (http://127.0.0.1:<port>, http://10.x.y.z),
exfiltrate via DNS / HTTP timing oracles even when the body is rejected by Image.open.
Arbitrary local file read via file://path (line 242) and the unguarded fallback Image.open(src) (line 248). Any file readable by the vLLM process is reachable through the model pipeline; with suitable formats this exposes /etc/passwd, ~/.aws/credentials, etc.
Server-side traffic generation / amplification by hammering arbitrary URLs from the vLLM host, with a 30-second timeout per request.

Suggested remediation

Replace direct requests.get and bare Image.open paths with MediaConnector.fetch_image / fetch_audio_async (or pass the inputs through MediaConnector before they reach the processor):

# vllm/transformers_utils/processors/mimo_v2_omni.py
from vllm.multimodal.utils import MediaConnector

_connector = MediaConnector()

def _fetch_image(src):
    if isinstance(src, Image.Image):
        return _to_rgb(src)
    if isinstance(src, bytes):
        return _to_rgb(copy.deepcopy(Image.open(BytesIO(src))))
    if isinstance(src, str):
        return _to_rgb(_connector.fetch_image(src))   # delegates to the hardened path
    raise ValueError(f"Unrecognized image source: {type(src)}")

Same change for the audio loader at line 471. This re-uses the SSRF allowlist, allowed_local_media_path policy, and size caps that the previous patches added.

Alternative: forbid str src from reaching the processor and require all multi-modal pre-processing to go through chat_utils.py / MediaConnector before hitting the model. Larger surface change, but completes the architectural fix.

Discovery

Static review on vllm@main (HEAD as of 2026-04-30) — found by triaging the file list against the three recent SSRF advisories: the mimo_v2_omni.py processor, added after those fixes, reintroduced the same bypass class.

Reporter

Ievgen Bondarenko — sactransport2000@gmail.com — GitHub @ibondarenko1

Severity

6.5 (Medium)


                  
                    CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.26.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-73560"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-09-08T20:42:00Z",
    "nvd_published_at": "2026-08-17T21:16:48Z",
    "severity": "MODERATE"
  },
  "details": "### Summary\n\n`vllm/transformers_utils/processors/mimo_v2_omni.py` \u2014 the multimodal processor for `MiMoV2OmniForCausalLM` \u2014 issues `requests.get(...)` directly on user-supplied image and audio URL strings and `Image.open(...)` on user-supplied local paths, **without** the SSRF / `allowed_local_media_path` checks that `vllm.multimodal.utils.MediaConnector` was hardened with in **GHSA-qh4c-xf7m-gxfc**, **GHSA-v359-jj2v-j536**, and **GHSA-pf3h-qjgv-vcpr**.\n\nThis is the same bug class as those three published advisories, in a code path the patches missed. When a user passes a URL or local-file string through `multi_modal_data` (e.g. `LLM.generate(multi_modal_data={\"image\": \"http://...\"})`), the processor takes the unsanitized string and dispatches it without any URL-scheme allowlist, network-target allowlist, size cap, or local-path allowlist.\n\n### Details\n\n**File:** `vllm/transformers_utils/processors/mimo_v2_omni.py` (current `main`)\n\n**Sink 1 \u2014 image SSRF + local-file read (`_fetch_image`, lines 231\u2013249):**\n\n```python\ndef _fetch_image(src: Any) -\u003e Image.Image:\n    if isinstance(src, Image.Image):\n        return _to_rgb(src)\n    if isinstance(src, bytes):\n        return _to_rgb(copy.deepcopy(Image.open(BytesIO(src))))\n    if isinstance(src, str):\n        if src.startswith((\"http://\", \"https://\")):\n            r = requests.get(src, timeout=30)              # SSRF: no allowlist, follows redirects\n            r.raise_for_status()\n            return _to_rgb(copy.deepcopy(Image.open(BytesIO(r.content))))\n        if src.startswith(\"file://\"):\n            return _to_rgb(Image.open(src[7:]))            # arbitrary local file read\n        if src.startswith(\"data:image\"):\n            ...\n        return _to_rgb(Image.open(src))                    # fallback also opens local files\n    raise ValueError(f\"Unrecognized image source: {type(src)}\")\n```\n\n**Sink 2 \u2014 audio SSRF (around line 471):**\n\n```python\nelif audio.startswith((\"http://\", \"https://\")):\n    r = requests.get(audio, timeout=30)                    # SSRF: same pattern\n    r.raise_for_status()\n    file_obj = io.BytesIO(r.content)\n```\n\n**Reachability.** `_fetch_image` is invoked from `MiMoVLProcessor.process_image`:\n\n```python\ndef process_image(self, image: ImageInput) -\u003e torch.Tensor:\n    kw = self._resolve_img_kw(image)\n    src = image.image\n    if isinstance(src, (str, bytes)):\n        src = _fetch_image(src)\n    ...\n```\n\n`MiMoVLProcessor` is wrapped by `MiMoV2OmniMultiModalProcessor` and registered for the `MiMoV2OmniForCausalLM` model architecture (`vllm/model_executor/models/mimo_v2_omni.py:1169`). Whenever a user passes a string into `multi_modal_data[\"image\"]` (or `[\"audio\"]`) for this model, the unsanitized URL/path reaches the sink.\n\n**Comparison to the recent fixes.** The remediation pattern adopted in the three earlier advisories was to route every external resource fetch through `MediaConnector`, which checks `allowed_local_media_path` and applies SSRF protection before issuing the network request. `chat_utils.py` (lines 838, 902, 924, 963, 1053, 1081) already uses `self._connector.fetch_image / fetch_audio / fetch_video`. The model processor in `mimo_v2_omni.py` was added later and skipped the connector \u2014 it calls `requests.get` and `Image.open` directly. Result: the public OpenAI chat-completion path is protected, but library use (`LLM.generate(multi_modal_data=...)`), batch processing, and any other path that lets a string reach the processor receive no protection.\n\n### Impact\n\n1. **SSRF \u2014 internal-network probing / cloud-metadata theft.** Standard `requests.get` follows redirects and accepts any URL. An attacker who controls a `multi_modal_data` value can:\n   - read AWS / GCP / Azure instance metadata (e.g. `http://169.254.169.254/latest/meta-data/iam/security-credentials/`),\n   - probe internal services on the vLLM host (`http://127.0.0.1:\u003cport\u003e`, `http://10.x.y.z`),\n   - exfiltrate via DNS / HTTP timing oracles even when the body is rejected by `Image.open`.\n2. **Arbitrary local file read** via `file://path` (line 242) and the unguarded fallback `Image.open(src)` (line 248). Any file readable by the vLLM process is reachable through the model pipeline; with suitable formats this exposes `/etc/passwd`, `~/.aws/credentials`, etc.\n3. **Server-side traffic generation / amplification** by hammering arbitrary URLs from the vLLM host, with a 30-second timeout per request.\n\n### Suggested remediation\n\nReplace direct `requests.get` and bare `Image.open` paths with `MediaConnector.fetch_image` / `fetch_audio_async` (or pass the inputs through `MediaConnector` before they reach the processor):\n\n```python\n# vllm/transformers_utils/processors/mimo_v2_omni.py\nfrom vllm.multimodal.utils import MediaConnector\n\n_connector = MediaConnector()\n\ndef _fetch_image(src):\n    if isinstance(src, Image.Image):\n        return _to_rgb(src)\n    if isinstance(src, bytes):\n        return _to_rgb(copy.deepcopy(Image.open(BytesIO(src))))\n    if isinstance(src, str):\n        return _to_rgb(_connector.fetch_image(src))   # delegates to the hardened path\n    raise ValueError(f\"Unrecognized image source: {type(src)}\")\n```\n\nSame change for the audio loader at line 471. This re-uses the SSRF allowlist, `allowed_local_media_path` policy, and size caps that the previous patches added.\n\nAlternative: forbid `str` `src` from reaching the processor and require all multi-modal pre-processing to go through `chat_utils.py` / `MediaConnector` before hitting the model. Larger surface change, but completes the architectural fix.\n\n### Discovery\n\nStatic review on `vllm@main` (HEAD as of 2026-04-30) \u2014 found by triaging the file list against the three recent SSRF advisories: the `mimo_v2_omni.py` processor, added after those fixes, reintroduced the same bypass class.\n\n### Reporter\n\nIevgen Bondarenko \u2014 `sactransport2000@gmail.com` \u2014 GitHub `@ibondarenko1`",
  "id": "GHSA-4hhp-h66f-j5j7",
  "modified": "2026-09-08T20:42:00Z",
  "published": "2026-09-08T20:42:00Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-73560"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/43117"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections"
}

PYSEC-2026-3934

Vulnerability from pysec - Published: 2026-09-10 09:45 - Updated: 2026-09-10 11:02

Details

Summary

Details

File: vllm/transformers_utils/processors/mimo_v2_omni.py (current main)

Sink 1 — image SSRF + local-file read (_fetch_image, lines 231–249):

def _fetch_image(src: Any) -> Image.Image:
    if isinstance(src, Image.Image):
        return _to_rgb(src)
    if isinstance(src, bytes):
        return _to_rgb(copy.deepcopy(Image.open(BytesIO(src))))
    if isinstance(src, str):
        if src.startswith(("http://", "https://")):
            r = requests.get(src, timeout=30)              # SSRF: no allowlist, follows redirects
            r.raise_for_status()
            return _to_rgb(copy.deepcopy(Image.open(BytesIO(r.content))))
        if src.startswith("file://"):
            return _to_rgb(Image.open(src[7:]))            # arbitrary local file read
        if src.startswith("data:image"):
            ...
        return _to_rgb(Image.open(src))                    # fallback also opens local files
    raise ValueError(f"Unrecognized image source: {type(src)}")

Sink 2 — audio SSRF (around line 471):

elif audio.startswith(("http://", "https://")):
    r = requests.get(audio, timeout=30)                    # SSRF: same pattern
    r.raise_for_status()
    file_obj = io.BytesIO(r.content)

Reachability. _fetch_image is invoked from MiMoVLProcessor.process_image:

def process_image(self, image: ImageInput) -> torch.Tensor:
    kw = self._resolve_img_kw(image)
    src = image.image
    if isinstance(src, (str, bytes)):
        src = _fetch_image(src)
    ...

Impact

SSRF — internal-network probing / cloud-metadata theft. Standard requests.get follows redirects and accepts any URL. An attacker who controls a multi_modal_data value can:
read AWS / GCP / Azure instance metadata (e.g. http://169.254.169.254/latest/meta-data/iam/security-credentials/),
probe internal services on the vLLM host (http://127.0.0.1:<port>, http://10.x.y.z),
exfiltrate via DNS / HTTP timing oracles even when the body is rejected by Image.open.
Arbitrary local file read via file://path (line 242) and the unguarded fallback Image.open(src) (line 248). Any file readable by the vLLM process is reachable through the model pipeline; with suitable formats this exposes /etc/passwd, ~/.aws/credentials, etc.
Server-side traffic generation / amplification by hammering arbitrary URLs from the vLLM host, with a 30-second timeout per request.

Suggested remediation

Replace direct requests.get and bare Image.open paths with MediaConnector.fetch_image / fetch_audio_async (or pass the inputs through MediaConnector before they reach the processor):

# vllm/transformers_utils/processors/mimo_v2_omni.py
from vllm.multimodal.utils import MediaConnector

_connector = MediaConnector()

def _fetch_image(src):
    if isinstance(src, Image.Image):
        return _to_rgb(src)
    if isinstance(src, bytes):
        return _to_rgb(copy.deepcopy(Image.open(BytesIO(src))))
    if isinstance(src, str):
        return _to_rgb(_connector.fetch_image(src))   # delegates to the hardened path
    raise ValueError(f"Unrecognized image source: {type(src)}")

Same change for the audio loader at line 471. This re-uses the SSRF allowlist, allowed_local_media_path policy, and size caps that the previous patches added.

Discovery

Reporter

Ievgen Bondarenko — sactransport2000@gmail.com — GitHub @ibondarenko1

Severity

6.5 (Medium)


                  
                    CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

Impacted products

Name	purl
vllm	pkg:pypi/vllm

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm",
        "purl": "pkg:pypi/vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.26.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.0.1",
        "0.1.0",
        "0.1.1",
        "0.1.2",
        "0.1.3",
        "0.1.4",
        "0.1.5",
        "0.1.6",
        "0.1.7",
        "0.10.0",
        "0.10.1",
        "0.10.1.1",
        "0.10.2",
        "0.11.0",
        "0.11.1",
        "0.11.2",
        "0.12.0",
        "0.13.0",
        "0.14.0",
        "0.14.1",
        "0.15.0",
        "0.15.1",
        "0.16.0",
        "0.17.0",
        "0.17.1",
        "0.18.0",
        "0.18.1",
        "0.19.0",
        "0.19.1",
        "0.2.0",
        "0.2.1",
        "0.2.1.post1",
        "0.2.2",
        "0.2.3",
        "0.2.4",
        "0.2.5",
        "0.2.6",
        "0.2.7",
        "0.20.0",
        "0.20.1",
        "0.20.2",
        "0.21.0",
        "0.22.0",
        "0.22.1",
        "0.23.0",
        "0.24.0",
        "0.25.0",
        "0.25.1",
        "0.3.0",
        "0.3.1",
        "0.3.2",
        "0.3.3",
        "0.4.0",
        "0.4.0.post1",
        "0.4.1",
        "0.4.2",
        "0.4.3",
        "0.5.0",
        "0.5.0.post1",
        "0.5.1",
        "0.5.2",
        "0.5.3",
        "0.5.3.post1",
        "0.5.4",
        "0.5.5",
        "0.6.0",
        "0.6.1",
        "0.6.1.post1",
        "0.6.1.post2",
        "0.6.2",
        "0.6.3",
        "0.6.3.post1",
        "0.6.4",
        "0.6.4.post1",
        "0.6.5",
        "0.6.6",
        "0.6.6.post1",
        "0.7.0",
        "0.7.1",
        "0.7.2",
        "0.7.3",
        "0.8.0",
        "0.8.1",
        "0.8.2",
        "0.8.3",
        "0.8.4",
        "0.8.5",
        "0.8.5.post1",
        "0.9.0",
        "0.9.0.1",
        "0.9.1",
        "0.9.2"
      ]
    }
  ],
  "aliases": [
    "CVE-2026-73560",
    "GHSA-4hhp-h66f-j5j7"
  ],
  "details": "### Summary\n\n`vllm/transformers_utils/processors/mimo_v2_omni.py` \u2014 the multimodal processor for `MiMoV2OmniForCausalLM` \u2014 issues `requests.get(...)` directly on user-supplied image and audio URL strings and `Image.open(...)` on user-supplied local paths, **without** the SSRF / `allowed_local_media_path` checks that `vllm.multimodal.utils.MediaConnector` was hardened with in **GHSA-qh4c-xf7m-gxfc**, **GHSA-v359-jj2v-j536**, and **GHSA-pf3h-qjgv-vcpr**.\n\nThis is the same bug class as those three published advisories, in a code path the patches missed. When a user passes a URL or local-file string through `multi_modal_data` (e.g. `LLM.generate(multi_modal_data={\"image\": \"http://...\"})`), the processor takes the unsanitized string and dispatches it without any URL-scheme allowlist, network-target allowlist, size cap, or local-path allowlist.\n\n### Details\n\n**File:** `vllm/transformers_utils/processors/mimo_v2_omni.py` (current `main`)\n\n**Sink 1 \u2014 image SSRF + local-file read (`_fetch_image`, lines 231\u2013249):**\n\n```python\ndef _fetch_image(src: Any) -\u003e Image.Image:\n    if isinstance(src, Image.Image):\n        return _to_rgb(src)\n    if isinstance(src, bytes):\n        return _to_rgb(copy.deepcopy(Image.open(BytesIO(src))))\n    if isinstance(src, str):\n        if src.startswith((\"http://\", \"https://\")):\n            r = requests.get(src, timeout=30)              # SSRF: no allowlist, follows redirects\n            r.raise_for_status()\n            return _to_rgb(copy.deepcopy(Image.open(BytesIO(r.content))))\n        if src.startswith(\"file://\"):\n            return _to_rgb(Image.open(src[7:]))            # arbitrary local file read\n        if src.startswith(\"data:image\"):\n            ...\n        return _to_rgb(Image.open(src))                    # fallback also opens local files\n    raise ValueError(f\"Unrecognized image source: {type(src)}\")\n```\n\n**Sink 2 \u2014 audio SSRF (around line 471):**\n\n```python\nelif audio.startswith((\"http://\", \"https://\")):\n    r = requests.get(audio, timeout=30)                    # SSRF: same pattern\n    r.raise_for_status()\n    file_obj = io.BytesIO(r.content)\n```\n\n**Reachability.** `_fetch_image` is invoked from `MiMoVLProcessor.process_image`:\n\n```python\ndef process_image(self, image: ImageInput) -\u003e torch.Tensor:\n    kw = self._resolve_img_kw(image)\n    src = image.image\n    if isinstance(src, (str, bytes)):\n        src = _fetch_image(src)\n    ...\n```\n\n`MiMoVLProcessor` is wrapped by `MiMoV2OmniMultiModalProcessor` and registered for the `MiMoV2OmniForCausalLM` model architecture (`vllm/model_executor/models/mimo_v2_omni.py:1169`). Whenever a user passes a string into `multi_modal_data[\"image\"]` (or `[\"audio\"]`) for this model, the unsanitized URL/path reaches the sink.\n\n**Comparison to the recent fixes.** The remediation pattern adopted in the three earlier advisories was to route every external resource fetch through `MediaConnector`, which checks `allowed_local_media_path` and applies SSRF protection before issuing the network request. `chat_utils.py` (lines 838, 902, 924, 963, 1053, 1081) already uses `self._connector.fetch_image / fetch_audio / fetch_video`. The model processor in `mimo_v2_omni.py` was added later and skipped the connector \u2014 it calls `requests.get` and `Image.open` directly. Result: the public OpenAI chat-completion path is protected, but library use (`LLM.generate(multi_modal_data=...)`), batch processing, and any other path that lets a string reach the processor receive no protection.\n\n### Impact\n\n1. **SSRF \u2014 internal-network probing / cloud-metadata theft.** Standard `requests.get` follows redirects and accepts any URL. An attacker who controls a `multi_modal_data` value can:\n   - read AWS / GCP / Azure instance metadata (e.g. `http://169.254.169.254/latest/meta-data/iam/security-credentials/`),\n   - probe internal services on the vLLM host (`http://127.0.0.1:\u003cport\u003e`, `http://10.x.y.z`),\n   - exfiltrate via DNS / HTTP timing oracles even when the body is rejected by `Image.open`.\n2. **Arbitrary local file read** via `file://path` (line 242) and the unguarded fallback `Image.open(src)` (line 248). Any file readable by the vLLM process is reachable through the model pipeline; with suitable formats this exposes `/etc/passwd`, `~/.aws/credentials`, etc.\n3. **Server-side traffic generation / amplification** by hammering arbitrary URLs from the vLLM host, with a 30-second timeout per request.\n\n### Suggested remediation\n\nReplace direct `requests.get` and bare `Image.open` paths with `MediaConnector.fetch_image` / `fetch_audio_async` (or pass the inputs through `MediaConnector` before they reach the processor):\n\n```python\n# vllm/transformers_utils/processors/mimo_v2_omni.py\nfrom vllm.multimodal.utils import MediaConnector\n\n_connector = MediaConnector()\n\ndef _fetch_image(src):\n    if isinstance(src, Image.Image):\n        return _to_rgb(src)\n    if isinstance(src, bytes):\n        return _to_rgb(copy.deepcopy(Image.open(BytesIO(src))))\n    if isinstance(src, str):\n        return _to_rgb(_connector.fetch_image(src))   # delegates to the hardened path\n    raise ValueError(f\"Unrecognized image source: {type(src)}\")\n```\n\nSame change for the audio loader at line 471. This re-uses the SSRF allowlist, `allowed_local_media_path` policy, and size caps that the previous patches added.\n\nAlternative: forbid `str` `src` from reaching the processor and require all multi-modal pre-processing to go through `chat_utils.py` / `MediaConnector` before hitting the model. Larger surface change, but completes the architectural fix.\n\n### Discovery\n\nStatic review on `vllm@main` (HEAD as of 2026-04-30) \u2014 found by triaging the file list against the three recent SSRF advisories: the `mimo_v2_omni.py` processor, added after those fixes, reintroduced the same bypass class.\n\n### Reporter\n\nIevgen Bondarenko \u2014 `sactransport2000@gmail.com` \u2014 GitHub `@ibondarenko1`",
  "id": "PYSEC-2026-3934",
  "modified": "2026-09-10T11:02:35.535229Z",
  "published": "2026-09-10T09:45:00.831333Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4hhp-h66f-j5j7"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-73560"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/43117"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/54503ecec0f3ac31e5ecfc5f28652e4cc42307b5"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/vllm"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-4hhp-h66f-j5j7"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections"
}

RHSA-2026:82059

Vulnerability from csaf_redhat - Published: 2026-10-13 06:58 - Updated: 2026-10-14 23:08

Summary

Red Hat Security Advisory: Red Hat AI Inference 3.5.2 (ROCm)

Severity

Critical

Scope

63 vulnerabilities in this advisory, including CVE-2026-73560.

CVE-2026-73560

A flaw was found in vLLM, an inference and serving engine for large language models. The MiMoV2OmniMultiModalProcessor component improperly handles attacker-controlled image and audio strings, bypassing security protections. This vulnerability allows a remote attacker to perform Server-Side Request Forgery (SSRF) and read arbitrary local files accessible to the vLLM process. Successful exploitation could lead to unauthorized access to internal network resources, cloud metadata, and sensitive local system files.

6.5 (Medium)


                
                  CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

Fixed: 1 product

https://access.redhat.com/errata/RHSA-2026:82059

Open the full advisory

RHSA-2026:82061

Vulnerability from csaf_redhat - Published: 2026-10-13 07:03 - Updated: 2026-10-14 23:08

Summary

Red Hat Security Advisory: Red Hat AI Inference Tech Preview 3.5.2 (Gaudi)

Severity

Critical

Scope

71 vulnerabilities in this advisory, including CVE-2026-73560.

CVE-2026-73560

6.5 (Medium)


                
                  CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

Fixed: 1 product

https://access.redhat.com/errata/RHSA-2026:82061

Open the full advisory

RHSA-2026:82368

Vulnerability from csaf_redhat - Published: 2026-10-13 17:47 - Updated: 2026-10-14 23:08

Summary

Red Hat Security Advisory: Red Hat AI Inference 3.5.2 (cuda)

Severity

Critical

Scope

71 vulnerabilities in this advisory, including CVE-2026-73560.

CVE-2026-73560

6.5 (Medium)


                
                  CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

Fixed: 2 products

https://access.redhat.com/errata/RHSA-2026:82368

Open the full advisory

RHSA-2026:82371

Vulnerability from csaf_redhat - Published: 2026-10-13 17:54 - Updated: 2026-10-14 23:08

Summary

Red Hat Security Advisory: Red Hat AI Inference 3.5.2 (spyre)

Severity

Critical

Scope

70 vulnerabilities in this advisory, including CVE-2026-73560.

CVE-2026-73560

6.5 (Medium)


                
                  CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

Fixed: 3 products

https://access.redhat.com/errata/RHSA-2026:82371

Open the full advisory

RHSA-2026:82415

Vulnerability from csaf_redhat - Published: 2026-10-13 19:20 - Updated: 2026-10-14 23:08

Summary

Red Hat Security Advisory: Red Hat AI Inference 3.5.2 (cpu)

Severity

Critical

Scope

71 vulnerabilities in this advisory, including CVE-2026-73560.

CVE-2026-73560

6.5 (Medium)


                
                  CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

Fixed: 1 product

https://access.redhat.com/errata/RHSA-2026:82415

Open the full advisory

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

Order JSON

Publication & reservation Sightings KEV catalogs Other timestamps

Loading timeline…

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted

CVE-2026-73560 (GCVE-0-2026-73560)

Summary

Details

Impact

Suggested remediation

Discovery

Reporter

Summary

Details

Impact

Suggested remediation

Discovery

Reporter

Tags

Sightings

Nomenclature

Vulnerability timeline

Related by attack behaviour