Octobre 2026

sgl-project sglang

SGLang through 0.5.22 in prefill/decode disaggregation mode contains a server-side request forgery vulnerability that allows unauthenticated attackers to trigger outbound requests via client-supplied bootstrap_host and bootstrap_port fields. Attackers sending crafted requests to the Decode worker's /generate endpoint can probe internal hosts and ports and block the shared scheduler loop, delaying other inference requests.

vllm-project vllm · Vllm vllm

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent users. This issue is fixed in version 0.30.0.