threatdeck
Live 14:45 UTC ·

AI Stack Alert Medium CVE-2026-115911 For AI Eng, AppSec, SOC / IR, CISO AI-assisted

vLLM <0.32.0: chat_template rendering DoS wedges all chat endpoints (CVE-2026-115911)

vLLM renders chat templates in a Jinja2 ImmutableSandboxedEnvironment with no wall-clock timeout, output-size cap, or loop/binop limit. The render runs in a thread pool with max_workers defaulting to 1, and a single crafted short template can block it until the process restarts. Affected versions are vllm >= 0.19.0 and < 0.32.0; the fix is in 0.32.0.

Why it matters

An authenticated API client, or a malicious model repo loaded with trust_remote_code=False, can deny chat inference to every tenant of the affected API-server replica. The string-multiplication variant can OOM-kill the API-server process.

Do this

  1. Upgrade vLLM to 0.32.0 or later on all API-server replicas.
  2. Until patched, restrict which clients can reach /v1/chat/completions, /v1/responses, /tokenize, /pooling and /invocations at the gateway, and limit API keys to trusted tenants.
  3. Review chat templates in tokenizer_config.json and any --chat-template input before loading untrusted model repos.
  4. Alert on chat endpoint timeouts, API-server process restarts, and OOM kills on vLLM hosts.

Exploit Clock

Exploitation unlikely (for now)

  • EPSS 0.31%

Signals

  • NoCISA KEV
  • 6.5CVSS
  • 0.31%EPSS
  • 27/100Priority
  • 85%Confidence

Evidence

“The render runs in a `ThreadPoolExecutor` whose `max_workers` defaults to **1**, and CPython worker threads cannot be interrupted.”

GitHub Security Advisories (AI packages)

“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.”

GitHub Security Advisories (AI packages)

“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`.”

GitHub Security Advisories (AI packages)

Sources

Affected / related

vLLM, chat_template Jinja2 rendering

Published 2026-10-28 21:14 UTC · updated 2026-11-08 02:47 UTC · AI-assisted summary, checked against quoted sources · How we score

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.