CVE-2026-109228 (GCVE-0-2026-109228)

Vulnerability from cvelistv5 – Published: 2026-10-12 14:04 – Updated: 2026-10-12 14:04
VLAI
Title
SGLang through 0.5.21 Resource Budget Bypass via GLM-V Video Parameters
Summary
SGLang through 0.5.21 contains a resource budget bypass vulnerability that allows remote attackers to override GLM-V video processing limits by supplying fps, max_frames, max_tokens_per_frame and max_image_tokens in the video_url object. Attackers can set these values arbitrarily high so glm4v.py decodes every frame of high-resolution video at full size, exhausting worker memory and denying service.
Severity
8.7 (High)
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
7.5 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CWE
  • CWE-770 - Allocation of Resources Without Limits or Throttling
Assigner
VulnCheck CNA under the mitre root
CNA scorecard B 84/100 over 5715 records in the last 180 days details
References
Impacted products
Vendor Product Version CPE status
sgl-project sglang Affected: 0 , ≤ 0.5.21 (semver)
    cpe:2.3:a:lmsys:sglang:*:*:*:*:*:*:*:*
Create a notification for this product.
Date Public
2026-10-11 00:00
Credits
Jiapeng Li Jiajia Liu Jiadai Wang
Show details on NVD website
To clipboard 

{
  "containers": {
    "cna": {
      "affected": [
        {
          "collectionURL": "https://pypi.org/project/sglang",
          "defaultStatus": "unaffected",
          "packageURL": "pkg:pypi/sglang",
          "product": "sglang",
          "repo": "https://github.com/sgl-project/sglang",
          "vendor": "sgl-project",
          "versions": [
            {
              "lessThanOrEqual": "0.5.21",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:lmsys:sglang:*:*:*:*:*:*:*:*",
                  "versionEndIncluding": "0.5.21",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Jiapeng Li"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Jiajia Liu"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Jiadai Wang"
        }
      ],
      "datePublic": "2026-10-11T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "SGLang through 0.5.21 contains a resource budget bypass vulnerability that allows remote attackers to override GLM-V video processing limits by supplying fps, max_frames, max_tokens_per_frame and max_image_tokens in the video_url object. Attackers can set these values arbitrarily high so glm4v.py decodes every frame of high-resolution video at full size, exhausting worker memory and denying service."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 8.7,
            "baseSeverity": "HIGH",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "NONE"
          },
          "format": "CVSS"
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 7.5,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
            "version": "3.1"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-770",
              "description": "Allocation of Resources Without Limits or Throttling",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-10-12T14:04:32.029Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "GitHub Issue #43705",
          "tags": [
            "issue-tracking"
          ],
          "url": "https://github.com/sgl-project/sglang/issues/43705"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/entrypoints/openai/protocol.py#L592-L594"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/parser/conversation.py#L691"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/multimodal/processors/glm4v.py#L160-L167"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/multimodal/processors/glm4v.py#L400"
        },
        {
          "tags": [
            "product"
          ],
          "url": "https://github.com/sgl-project/sglang"
        },
        {
          "name": "VulnCheck Advisory: SGLang through 0.5.21 Resource Budget Bypass via GLM-V Video Parameters",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/sglang-through-0.5.21-resource-budget-bypass-via-glm-v-video-parameters"
        }
      ],
      "title": "SGLang through 0.5.21 Resource Budget Bypass via GLM-V Video Parameters",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-109228",
    "datePublished": "2026-10-12T14:04:32.029Z",
    "dateReserved": "2026-10-12T13:46:33.333Z",
    "dateUpdated": "2026-10-12T14:04:32.029Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "collectionURL": "https://pypi.org/project/sglang",
                "defaultStatus": "unaffected",
                "packageURL": "pkg:pypi/sglang",
                "product": "sglang",
                "repo": "https://github.com/sgl-project/sglang",
                "vendor": "sgl-project",
                "versions": [
                  {
                    "lessThanOrEqual": "0.5.21",
                    "status": "affected",
                    "version": "0",
                    "versionType": "semver"
                  }
                ]
              }
            ],
            "source": "disclosure@vulncheck.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "SGLang through 0.5.21 contains a resource budget bypass vulnerability that allows remote attackers to override GLM-V video processing limits by supplying fps, max_frames, max_tokens_per_frame and max_image_tokens in the video_url object. Attackers can set these values arbitrarily high so glm4v.py decodes every frame of high-resolution video at full size, exhausting worker memory and denying service."
          }
        ],
        "id": "CVE-2026-109228",
        "lastModified": "2026-10-12T14:17:12.207",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 7.5,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "NONE",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
                "version": "3.1"
              },
              "exploitabilityScore": 3.9,
              "impactScore": 3.6,
              "source": "disclosure@vulncheck.com",
              "type": "Primary"
            }
          ],
          "cvssMetricV40": [
            {
              "cvssData": {
                "Automatable": "NOT_DEFINED",
                "Recovery": "NOT_DEFINED",
                "Safety": "NOT_DEFINED",
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "availabilityRequirement": "NOT_DEFINED",
                "baseScore": 8.7,
                "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": "NONE",
                "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:N/UI:N/VC:N/VI:N/VA:H/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": "HIGH",
                "vulnConfidentialityImpact": "NONE",
                "vulnIntegrityImpact": "NONE",
                "vulnerabilityResponseEffort": "NOT_DEFINED"
              },
              "source": "disclosure@vulncheck.com",
              "type": "Secondary"
            }
          ]
        },
        "published": "2026-10-12T14:17:12.087",
        "references": [
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/entrypoints/openai/protocol.py#L592-L594"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/multimodal/processors/glm4v.py#L160-L167"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/multimodal/processors/glm4v.py#L400"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/parser/conversation.py#L691"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang/issues/43705"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://www.vulncheck.com/advisories/sglang-through-0.5.21-resource-budget-bypass-via-glm-v-video-parameters"
          }
        ],
        "sourceIdentifier": "disclosure@vulncheck.com",
        "vulnStatus": "Deferred",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-770"
              }
            ],
            "source": "disclosure@vulncheck.com",
            "type": "Primary"
          }
        ]
      }
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

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.



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.