Vulnerability-Lookup

PYSEC-2026-4344

Vulnerability from pysec - Published: 2026-10-26 17:17 - Updated: 2026-10-29 10:34

Details

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0.

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
vllm	pkg:pypi/vllm

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "ecosystem_specific": {},
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm",
        "purl": "pkg:pypi/vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.19.0"
            },
            {
              "fixed": "0.32.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.19.0",
        "0.19.1",
        "0.20.0",
        "0.20.1",
        "0.20.2",
        "0.21.0",
        "0.22.0",
        "0.22.1",
        "0.23.0",
        "0.24.0",
        "0.25.0",
        "0.25.1",
        "0.26.0",
        "0.27.0",
        "0.27.1",
        "0.28.0",
        "0.29.0",
        "0.30.0",
        "0.31.0"
      ]
    }
  ],
  "aliases": [
    "CVE-2026-115911",
    "GHSA-542m-9234-8gvf"
  ],
  "details": "vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0.",
  "id": "PYSEC-2026-4344",
  "modified": "2026-10-29T10:34:17.227714Z",
  "published": "2026-10-26T17:17:18.753Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/pull/50300"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf"
    }
  ],
  "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-2026-115911 (GCVE-0-2026-115911)

Vulnerability from cvelistv5 – Published: 2026-10-26 16:47 – Updated: 2026-10-26 16:47

Title

vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool

Summary

Severity

6.5 (Medium)


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

CWE

CWE-400 - Uncontrolled Resource Consumption
CWE-770 - Allocation of Resources Without Limits or Throttling
CWE-834 - Excessive Iteration

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7926 records in the last 180 days details

References

4 references

URL	Tags
https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
https://github.com/vllm-project/vllm/pull/50300	x_refsource_MISC
https://github.com/vllm-project/vllm/commit/cff08…	x_refsource_MISC
https://github.com/vllm-project/vllm/releases/tag…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
vllm-project	vllm	Affected: >= 0.19.0, < 0.32.0

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.19.0, \u003c 0.32.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0."
        }
      ],
      "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-400",
              "description": "CWE-400: Uncontrolled Resource Consumption",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-770",
              "description": "CWE-770: Allocation of Resources Without Limits or Throttling",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-834",
              "description": "CWE-834: Excessive Iteration",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-10-26T16:47:59.377Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/50300",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/50300"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134"
        },
        {
          "name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
        }
      ],
      "source": {
        "advisory": "GHSA-542m-9234-8gvf",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-115911",
    "datePublished": "2026-10-26T16:47:59.377Z",
    "dateReserved": "2026-10-23T20:21:45.107Z",
    "dateUpdated": "2026-10-26T16:47:59.377Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

GHSA-542M-9234-8GVF

Vulnerability from github – Published: 2026-10-28 21:14 – Updated: 2026-10-28 21:14

Summary

vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool

Details

Summary

vLLM renders chat templates by passing the resolved Jinja2 source to tokenizer.apply_chat_template(), which compiles and .render()s it in an ImmutableSandboxedEnvironment. The sandbox prevents code-execution escapes but imposes no wall-clock timeout, no output-size cap, and no nested-loop or binop limit. The render runs in a ThreadPoolExecutor whose max_workers defaults to 1, and CPython worker threads cannot be interrupted. An authenticated API client (or a malicious model repo loaded with trust_remote_code=False) can therefore submit a single short template and permanently wedge all chat-style endpoints (/v1/chat/completions, /v1/responses, /tokenize, /pooling-chat, /invocations-chat) for every tenant until the process is restarted. A string-multiplication variant instead OOM-kills the API-server process. Because of a separately-reported (GHSA-jmjw-q4x3-hmc2) gate omission on /v1/responses, the remote authenticated attacker vector works in default vllm serve configuration with no operator opt-in.

Impact

A single authenticated request of <100 bytes permanently denies all chat-style inference (/v1/chat/completions, /v1/responses, /tokenize, /pooling-chat, /invocations-chat) to every tenant of the API-server replica until the operator restarts the process. The string-multiplication variant OOM-kills the process. In a multi-tenant deployment this is a cross-tenant denial-of-service from any one tenant. From the malicious-model angle, a model repo whose tokenizer_config.json carries the hostile template wedges every replica that loads it on the first legitimate chat request, with trust_remote_code=False.

Preconditions: any non-harmony model (model_type != gpt_oss); renderer_num_workers at its default of 1; for the default-config authenticated API attacker vector, --chat-template must be unset (the default because most HF models ship their own). Blast radius: API-server process, per replica. Engine/worker processes unaffected by the CPU variant (event loop survives); affected by the memory variant (process OOM). Persistence: until process restart. Survives client disconnect.

This advisory was fixed in MR50300.

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": "0.19.0"
            },
            {
              "fixed": "0.32.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-115911"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-400",
      "CWE-770",
      "CWE-834"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-10-28T21:14:52Z",
    "nvd_published_at": "2026-10-26T17:17:18Z",
    "severity": "MODERATE"
  },
  "details": "### Summary\nvLLM renders chat templates by passing the resolved Jinja2 source to `tokenizer.apply_chat_template()`, which compiles and `.render()`s it in an `ImmutableSandboxedEnvironment`. The sandbox prevents code-execution escapes but imposes **no wall-clock timeout, no output-size cap, and no nested-loop or binop limit**. The render runs in a `ThreadPoolExecutor` whose `max_workers` defaults to **1**, and CPython worker threads cannot be interrupted. An authenticated API client (or a malicious model repo loaded with `trust_remote_code=False`) can therefore submit a single short template and permanently wedge **all** chat-style endpoints (`/v1/chat/completions`, `/v1/responses`, `/tokenize`, `/pooling`-chat, `/invocations`-chat) for every tenant until the process is restarted. A string-multiplication variant instead OOM-kills the API-server process. Because of a separately-reported (GHSA-jmjw-q4x3-hmc2) gate omission on `/v1/responses`, the remote authenticated attacker vector works in **default `vllm serve` configuration** with no operator opt-in.\n\n### Impact\nA single authenticated request of \u003c100 bytes permanently denies all chat-style inference (`/v1/chat/completions`, `/v1/responses`, `/tokenize`, `/pooling`-chat, `/invocations`-chat) to **every tenant** of the API-server replica until the operator restarts the process. The string-multiplication variant OOM-kills the process. In a multi-tenant deployment this is a cross-tenant denial-of-service from any one tenant. From the malicious-model angle, a model repo whose `tokenizer_config.json` carries the hostile template wedges every replica that loads it on the first legitimate chat request, with `trust_remote_code=False`.\n\n**Preconditions:** any non-harmony model (`model_type != gpt_oss`); `renderer_num_workers` at its default of 1; for the default-config authenticated API attacker vector, `--chat-template` must be unset (the default because most HF models ship their own).\n**Blast radius:** API-server process, per replica. Engine/worker processes unaffected by the CPU variant (event loop survives); affected by the memory variant (process OOM).\n**Persistence:** until process restart. Survives client disconnect.\n\nThis advisory was fixed in [MR50300](https://github.com/vllm-project/vllm/pull/50300).",
  "id": "GHSA-542m-9234-8gvf",
  "modified": "2026-10-28T21:14:52Z",
  "published": "2026-10-28T21:14:52Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-115911"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/50300"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
    }
  ],
  "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 via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool"
}

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

PYSEC-2026-4344

CVE-2026-115911 (GCVE-0-2026-115911)

GHSA-542M-9234-8GVF

Summary

Impact

Tags

Sightings

Nomenclature

Vulnerability timeline

Related by attack behaviour