Vulnerability-Lookup

CVE-2026-93688 (GCVE-0-2026-93688)

Vulnerability from cvelistv5 – Published: 2026-09-18 15:06 – Updated: 2026-09-18 16:23

Title

SGLang through 0.5.19 Unbounded Memory Allocation via bootstrap_room

Summary

SGLang through 0.5.19 in prefill/decode disaggregation mode with Mooncake KV transfer backend fails to validate bootstrap_room values, allowing unbounded transfer state allocation. Unauthenticated attackers can reach the decode engine's POST /generate endpoint and submit arbitrary bootstrap_room values to exhaust prefill process memory until out-of-memory termination.

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 mitre root

References

7 references

URL	Tags
https://github.com/sgl-project/sglang/issues/39428	issue-tracking
https://github.com/sgl-project/sglang	product
https://github.com/sgl-project/sglang/blob/v0.5.1…	technical-description
https://github.com/sgl-project/sglang/blob/v0.5.1…	technical-description
https://github.com/sgl-project/sglang/blob/v0.5.1…	technical-description
https://github.com/sgl-project/sglang/blob/v0.5.1…	technical-description
https://www.vulncheck.com/advisories/sglang-throu…	third-party-advisory

Impacted products

1 product

Vendor	Product	Version	CPE status
sgl-project	sglang	Affected: 0 , ≤ 0.5.19 (semver) cpe:2.3:a:lmsys:sglang::::::::

Date Public

2026-09-14 00:00

Credits

Jiapeng Li Mingkai Yu Jiajia Liu

Show details on NVD website

JSON

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": "0.5.19",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:lmsys:sglang:*:*:*:*:*:*:*:*",
                  "versionEndIncluding": "0.5.19",
                  "vulnerable": true
                }
              ],
              "operator": "OR"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Jiapeng Li"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Mingkai Yu"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Jiajia Liu"
        }
      ],
      "datePublic": "2026-09-14T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "SGLang through 0.5.19 in prefill/decode disaggregation mode with Mooncake KV transfer backend fails to validate bootstrap_room values, allowing unbounded transfer state allocation. Unauthenticated attackers can reach the decode engine\u0027s POST /generate endpoint and submit arbitrary bootstrap_room values to exhaust prefill process memory until out-of-memory termination."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 8.7,
            "baseSeverity": "HIGH",
            "exploitMaturity": "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",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "NONE",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "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",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-770",
              "description": "Allocation of Resources Without Limits or Throttling",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-09-18T16:23:59.301Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "GitHub Issue #39428",
          "tags": [
            "issue-tracking"
          ],
          "url": "https://github.com/sgl-project/sglang/issues/39428"
        },
        {
          "tags": [
            "product"
          ],
          "url": "https://github.com/sgl-project/sglang"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/disaggregation/mooncake/conn.py#L2118-L2119"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/disaggregation/mooncake/conn.py#L1988-L1990"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/managers/io_struct.py#L281"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/managers/scheduler.py#L2672-L2690"
        },
        {
          "name": "VulnCheck Advisory: SGLang through 0.5.19 Unbounded Memory Allocation via bootstrap_room",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/sglang-through-0.5.19-unbounded-memory-allocation-via-bootstrap-room"
        }
      ],
      "title": "SGLang through 0.5.19 Unbounded Memory Allocation via bootstrap_room",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-93688",
    "datePublished": "2026-09-18T15:06:03.530Z",
    "dateReserved": "2026-09-18T14:39:01.470Z",
    "dateUpdated": "2026-09-18T16:23:59.301Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-93688",
      "date": "2026-09-19",
      "epss": "0.00396",
      "percentile": "0.33596"
    },
    "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": "0.5.19",
                    "status": "affected",
                    "version": "0",
                    "versionType": "semver"
                  }
                ]
              }
            ],
            "source": "disclosure@vulncheck.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "SGLang through 0.5.19 in prefill/decode disaggregation mode with Mooncake KV transfer backend fails to validate bootstrap_room values, allowing unbounded transfer state allocation. Unauthenticated attackers can reach the decode engine\u0027s POST /generate endpoint and submit arbitrary bootstrap_room values to exhaust prefill process memory until out-of-memory termination."
          }
        ],
        "id": "CVE-2026-93688",
        "lastModified": "2026-09-18T16:17:15.683",
        "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": "2026-09-18T16:17:15.683",
        "references": [
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/disaggregation/mooncake/conn.py#L1988-L1990"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/disaggregation/mooncake/conn.py#L2118-L2119"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/managers/io_struct.py#L281"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/managers/scheduler.py#L2672-L2690"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://github.com/sgl-project/sglang/issues/39428"
          },
          {
            "source": "disclosure@vulncheck.com",
            "url": "https://www.vulncheck.com/advisories/sglang-through-0.5.19-unbounded-memory-allocation-via-bootstrap-room"
          }
        ],
        "sourceIdentifier": "disclosure@vulncheck.com",
        "vulnStatus": "Received",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-770"
              }
            ],
            "source": "disclosure@vulncheck.com",
            "type": "Primary"
          }
        ]
      }
    }
  }
}

GHSA-HPQJ-J2XW-Q3CX

Vulnerability from github – Published: 2026-09-18 18:31 – Updated: 2026-09-18 18:31

Details

Severity

7.5 (High)


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

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

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2026-93688"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-770"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-09-18T16:17:15Z",
    "severity": "HIGH"
  },
  "details": "SGLang through 0.5.19 in prefill/decode disaggregation mode with Mooncake KV transfer backend fails to validate bootstrap_room values, allowing unbounded transfer state allocation. Unauthenticated attackers can reach the decode engine\u0027s POST /generate endpoint and submit arbitrary bootstrap_room values to exhaust prefill process memory until out-of-memory termination.",
  "id": "GHSA-hpqj-j2xw-q3cx",
  "modified": "2026-09-18T18:31:41Z",
  "published": "2026-09-18T18:31:41Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-93688"
    },
    {
      "type": "WEB",
      "url": "https://github.com/sgl-project/sglang/issues/39428"
    },
    {
      "type": "WEB",
      "url": "https://github.com/sgl-project/sglang"
    },
    {
      "type": "WEB",
      "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/disaggregation/mooncake/conn.py#L1988-L1990"
    },
    {
      "type": "WEB",
      "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/disaggregation/mooncake/conn.py#L2118-L2119"
    },
    {
      "type": "WEB",
      "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/managers/io_struct.py#L281"
    },
    {
      "type": "WEB",
      "url": "https://github.com/sgl-project/sglang/blob/v0.5.19/python/sglang/srt/managers/scheduler.py#L2672-L2690"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/sglang-through-0.5.19-unbounded-memory-allocation-via-bootstrap-room"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "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",
      "type": "CVSS_V4"
    }
  ]
}

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.

Detection rules are retrieved from Rulezet.

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.