vLLM multimodal processor input validation insufficiency leads to denial of service

1. Time not given
   GitHub 安全公告Selected

   vLLM discloses remote denial-of-service vulnerability due to insufficient input validation in multimodal processors

   vLLM's multimodal requests can pass insufficiently validated processor parameters to image and video processors, leading to excessive resource allocation, memory exhaustion in the shared serving process, and interruption. The issue involves processors such as Isaac, InternVL, H2OVL, and shared input boundaries; deployments without an external authentication layer may be triggered by unauthenticated clients. Maintainers fixed this by rejecting request-level processor overrides by default, requiring trusted clients to explicitly enable them. The advisory states that this request-level field was introduced in v0.7.3, with the fixed version being 0.31.0.

2. Time not given
   GitHub 安全公告Selected

   vLLM v0.29.0 unauthenticated generation endpoint can be hung by a single request while health checks still return 200

   vLLM's /inference/v1/generate path does not fully validate generation parameters; an exception can cause the EngineCore input thread to exit, after which all requests hang while the process and /health still respond normally. The advisory reproduces this in v0.29.0: the endpoint is mounted by default and can be accessed by unauthenticated network clients when --api-key is not set. This example shows that a health check alone cannot prove the inference service is still usable. The GitHub advisory marks affected versions as < 0.31.0 and the fixed version as 0.31.0.

Current attention61·Peak in the comparable period65（Oct 8 09:00）·Change over the comparable past 24 hours 0%