Vulnerability-Lookup

PYSEC-2025-235

Vulnerability from pysec - Published: 2025-04-09 16:15 - Updated: 2026-05-20 09:19

Details

XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to 0.1.18, Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host's memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur. This vulnerability is fixed in 0.1.18.

Severity

6.5 (Medium)


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

Impacted products

Name	purl
xgrammar	pkg:pypi/xgrammar

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "xgrammar",
        "purl": "pkg:pypi/xgrammar"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.1.18"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.1.0",
        "0.1.1",
        "0.1.10",
        "0.1.11",
        "0.1.12",
        "0.1.13",
        "0.1.14",
        "0.1.15",
        "0.1.16",
        "0.1.17",
        "0.1.2",
        "0.1.3",
        "0.1.4",
        "0.1.4rc2",
        "0.1.5",
        "0.1.5rc1",
        "0.1.6",
        "0.1.7",
        "0.1.8",
        "0.1.9"
      ]
    }
  ],
  "aliases": [
    "CVE-2025-32381",
    "GHSA-389x-67px-mjg3"
  ],
  "details": "XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to 0.1.18, Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host\u0027s memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur. This vulnerability is fixed in 0.1.18.",
  "id": "PYSEC-2025-235",
  "modified": "2026-05-20T09:19:24.371536Z",
  "published": "2025-04-09T16:15:26.210Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3"
    },
    {
      "type": "FIX",
      "url": "https://github.com/mlc-ai/xgrammar/pull/243"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/pull/16283"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ]
}

CVE-2025-32381 (GCVE-0-2025-32381)

Vulnerability from cvelistv5 – Published: 2025-04-09 16:00 – Updated: 2025-04-09 20:43

Title

Denial of Service by abusing xgrammar unbounded cache in memory

Summary

Severity

6.5 (Medium)


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

SSVC

Exploitation: none Automatable: no Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2025-04-09 17:26 UTC

CWE

CWE-770 - Allocation of Resources Without Limits or Throttling

Assigner

GitHub_M mitre root Scorecard

References

3 references

URL	Tags
https://github.com/mlc-ai/xgrammar/security/advis…	x_refsource_CONFIRM
https://github.com/mlc-ai/xgrammar/pull/243	x_refsource_MISC
https://github.com/vllm-project/vllm/pull/16283	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
mlc-ai	xgrammar	Affected: < 0.1.18

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-32381",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-04-09T17:26:48.431586Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-04-09T20:43:33.169Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "xgrammar",
          "vendor": "mlc-ai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.1.18"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to 0.1.18, Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host\u0027s memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur. This vulnerability is fixed in 0.1.18."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 6.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-770",
              "description": "CWE-770: Allocation of Resources Without Limits or Throttling",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-04-09T16:00:10.642Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3"
        },
        {
          "name": "https://github.com/mlc-ai/xgrammar/pull/243",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/mlc-ai/xgrammar/pull/243"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/16283",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/16283"
        }
      ],
      "source": {
        "advisory": "GHSA-389x-67px-mjg3",
        "discovery": "UNKNOWN"
      },
      "title": "Denial of Service by abusing xgrammar unbounded cache in memory"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-32381",
    "datePublished": "2025-04-09T16:00:10.642Z",
    "dateReserved": "2025-04-06T19:46:02.462Z",
    "dateUpdated": "2025-04-09T20:43:33.169Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

GHSA-389X-67PX-MJG3

Vulnerability from github – Published: 2025-04-09 13:08 – Updated: 2026-06-08 20:04

Summary

xgrammar Vulnerable to Denial of Service (DoS) by abusing unbounded cache in memory

Details

Summary

Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host's memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur.

Details

The fix is to add a limit to the cache size. This was done in https://github.com/mlc-ai/xgrammar/pull/243

An example of making use of the new cache size limit can be found in vLLM here: https://github.com/vllm-project/vllm/pull/16283

Impact

Any system making use of Xgrammar and taking requests as input from potentially untrusted parties would be vulnerable to this denial of service issue.

Severity

6.5 (Medium)


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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "xgrammar"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.1.18"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-32381"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-770"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-04-09T13:08:59Z",
    "nvd_published_at": "2025-04-09T16:15:26Z",
    "severity": "MODERATE"
  },
  "details": "### Summary\n\nXgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host\u0027s memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur.\n\n### Details\n\nThe fix is to add a limit to the cache size. This was done in https://github.com/mlc-ai/xgrammar/pull/243\n\nAn example of making use of the new cache size limit can be found in vLLM here: https://github.com/vllm-project/vllm/pull/16283\n\n### Impact\n\nAny system making use of Xgrammar and taking requests as input from potentially untrusted parties would be vulnerable to this denial of service issue.",
  "id": "GHSA-389x-67px-mjg3",
  "modified": "2026-06-08T20:04:11Z",
  "published": "2025-04-09T13:08:59Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-32381"
    },
    {
      "type": "WEB",
      "url": "https://github.com/mlc-ai/xgrammar/pull/243"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/16283"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/mlc-ai/xgrammar"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/xgrammar/PYSEC-2025-235.yaml"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "xgrammar Vulnerable to Denial of Service (DoS) by abusing unbounded cache in memory"
}

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.

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

PYSEC-2025-235

CVE-2025-32381 (GCVE-0-2025-32381)

GHSA-389X-67PX-MJG3

Summary

Details

Impact

Tags

Sightings

Nomenclature

Related by attack behaviour