UTC
Medium

Unvalidated stop_token_ids causes engine crash (DoS) and out-of-bounds GPU write

GHSA-w9r6-29q4-pvpr · published 2026-10-09

Severity
Medium
CVSS score
6.5
Chance of exploitation (EPSS)
No CVE
Fixed in
0.29.0
What it is

A single request containing an out-of-vocabulary stop token could terminate the engine and interrupt service for other users. On the V2 runner, the same unchecked index could corrupt adjacent logits or other GPU state.

What to do

Upgrade vllm to 0.29.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

PR #54196 validates every stop_token_ids value against the model vocabulary before it reaches the sampler. Invalid IDs are rejected as request errors.

Affected
PackageRegistryAffectedFixed in
vllmPyPI>= 0.20.1, < 0.29.00.29.0

The impact, patch and workaround text comes from the advisory, shortened (published by vLLM). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].