Advisory Catalog

vLLM from 0.20.0 before 0.30.0 contains a denial of service vulnerability that allows remote attackers to crash the engine by sending inconsistent multimodal metadata to the disaggregated /inference/v1/generate endpoint. Attackers can replay a valid multimodal item with repeated or overlapping mm_pl

vLLM from 0.10.2 before 0.25.0 contains an uncontrolled resource consumption vulnerability that allows unauthenticated attackers to exhaust memory because the Nemotron-VL processors globally set Image.MAX_IMAGE_PIXELS to None. Attackers can submit a pathological decompression-bomb image to /v1/chat/

vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery vulnerability that allows API callers to force outbound connections by embedding a decode address in the X-Request-Id header. Attackers can make a P2pNcclConnector prefill worker ZMQ-connect to an attacker host, leaking the NCCL un

vLLM from 0.22.0 before 0.24.0 contains a denial of service vulnerability that allows remote attackers to terminate EngineCore by bypassing logprob_token_ids limits in the Rust gRPC frontend. Attackers can send Generate or GenerateStream requests with output_logprobs enabled and more than 128 output

filelock: ReadWriteLock on Windows acts on SQLite side files another local user places beside its database

filelock: On Windows an oplock on a soft lock's marker holds SoftFileLock.acquire() past its timeout and blocks the stale break

graphql-scalars PhoneNumber scalar is vulnerable to regular expression denial of service

LangGraph CLI prints the registry push token in `langgraph deploy --verbose` output

Serialize JavaScript: Cross-site scripting (XSS) via unescaped </script at the end of a serialized function body

MLflow: SSRF on unauthenticated MLflow servers via third-party scorer kwargs in the scorer invoke, register, and GenAI evaluate endpoints

LangGraph: Namespace labels containing `.` reach other namespaces in Postgres and SQLite stores