UTC
Medium

vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds

CVE-2026-71486 · GHSA-8737-qx52-hjff · published 2026-09-04

Severity
Medium
CVSS score
4.3
Chance of exploitation (EPSS)
0.37%
Fixed in
0.26.0
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Partial
  • CISA SSVC
What it is

An attacker with access to the /v1 API can send derender requests that consume CPU and memory in the frontend/postprocessing process and can cause large responses unrelated to any bounded generation. In disaggregated deployments, this affects the CPU-only render frontend; in servers where the render router is attached alongside generation, it affects the same OpenAI-compatible server process that handles normal client traffic. This can degrade availability for other clients sharing the process. Likely CWE: CWE-400 (Uncontrolled Resource Consumption) / CWE-770 (Allocation of Resources Without Limits or Throttling). Conservative CVSS v3.1: (4.3).

What to do

Upgrade vllm to 0.26.0 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.

Validate derender payloads before any detokenization or parser invocation. Apply bounded limits to generateresponse(s), choices, tokenids, promptlogprobs, logprobs.content, toplogprobs, and routedexperts that are at least as strict as the corresponding generation-side limits. For completions, reject generateresponses counts above the number of prompts that /v1/completions/render would have produced, and reject total nested choice counts above maxnumseqs / n limits.

Affected
PackageRegistryAffectedFixed in
vllmPyPI< 0.26.00.26.0

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). 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].