Tools AI Risk Radar ai-incident-0089
Incident record
Four vLLM advisories in one day, each an unauthenticated request that stalls or bloats the server
- Severity
- Medium
- Status
- Patched
- Type
- Infra Vuln
- Target
- vLLM before 0.29.0
- Actor
- researcher
What happened
Four denial-of-service advisories published together and fixed in 0.29.0: an unbounded cache_salt parameter that stalls the single scheduler thread, audio decoding that ignores the configured clip-size limit, sampler-subclass attribute shadowing that bypasses decoder-slot and GPU-memory limits, and remote media fetched in full across four ingress paths before size limits apply. CVSS scores run 3.7 to 6.5 and none carries a CVE yet.
All four are reachable without credentials on exposed endpoints. The remote-media advisory is the widest: any of four ingress paths materialises the whole fetch before checking size.
Sources
- vLLM advisory GHSA-wpww-v874-ph2pgithub.com/vllm-project/vllm/security/advisories/GHSA-wpww-v…
- vLLM advisory GHSA-p6g9-7v3x-m8mvgithub.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7…
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 · 18 September 2026