Tools AI Risk Radar ai-incident-0249
Incident record
vLLM chat templates could block shared rendering
- Severity
- Medium
- Status
- Patched
- Type
- Infra Vuln
- Target
- vllm-project/vllm
- Actor
- researcher
What happened
An attacker-controlled chat template could keep a rendering worker busy or exhaust memory and interrupt other users’ chat requests.
The report describes an authenticated API route and a malicious model-repository route. The template renderer lacked time and output limits. The maintainer lists the affected range from 0.19.0 and identifies 0.32.0 as patched.
Sources
- Maintainer security advisorygithub.com/vllm-project/vllm/security/advisories/GHSA-542m-9…
One record from the AI Risk Radar, maintained by the Security Desk.Data: CSV · JSON ·RSS · CC BY 4.0 with attribution to YFarmX.Tracker updated · 28 October 2026