Database/AI/ML frameworks & serving
vLLM OpenAI-compatible server (chat_template / chat_template_kwargs): NOISY-NEIGHBOUR DENIAL OF SERVICE: one tenant
Impact
NOISY-NEIGHBOUR DENIAL OF SERVICE: one tenant takes down a shared inference endpoint, and the GPU sits idle while it happens. The OpenAI-compatible server lets callers supply a Jinja template through chat_template. Jinja has loops and nesting, so a small request body can pin CPU and balloon memory until the server stops answering anyone. The operationally important detail is that blocking the chat_template parameter is not enough: the server builds its kwargs dict and then calls dict.update() with the caller's chat_template_kwargs, so an attacker simply nests a chat_template key inside chat_template_kwargs and overwrites the template anyway. Any filtering you wrote against the obvious parameter name misses the real one. On a GPU fleet the cost is the expensive resource stranded behind a wedged Python process, plus every co-tenant on that replica losing service.
Who can reach it
Network, any client authenticated to the OpenAI-compatible endpoint, if that endpoint accepts chat_template or chat_template_kwargs from untrusted callers. A single ordinary-looking chat completion request is sufficient.
What to do
Upgrade vLLM to 0.11.0 or later and restart the servers. If you front vLLM with a gateway, strip both chat_template and chat_template_kwargs from inbound requests — stripping only chat_template does not close it. Set per-pod CPU and memory limits with a restart policy so a wedged replica is recycled rather than dragging the node, and rate-limit per tenant.
References
Related entries
- Ray (GCS Redis credential handling / logging): When the Redis password is passed on the Ray command line it getsCVE-2025-1979 · Ray (GCS Redis credential handling / logging)Medium
- KServe ModelMesh: Group-writable `/etc/passwd` in the container imageCVE-2025-57852 · KServe ModelMeshMedium
- NVIDIA OpenShell: tunnels opened before a policy reload keep running under the old network policyCVE-2026-100970 · NVIDIA OpenShell for Linux (network policy hot-reload)Medium
- NVIDIA OpenShell: nonstandard HTTP methods bypass L7 policy on CONNECT tunnelsCVE-2026-100973 · NVIDIA OpenShell for Linux (L7 policy for HTTP CONNECT tunnels)Medium
- NVIDIA OpenShell: gateway accepts any sandbox host key, enabling machine-in-the-middleCVE-2026-100978 · NVIDIA OpenShell for Linux (gateway-to-sandbox transport)Medium
- NVIDIA OpenShell: HTTP request smuggling past the L7 REST proxy's policy checksCVE-2026-100981 · NVIDIA OpenShell for Linux (L7 REST proxy)Medium
This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.