CVE-2026-77776

Headroom LLM proxy (v0.29.0 and earlier) trusts the client-supplied x-headroom-user-id header as an authenticated identity without binding it to the caller. The header is read directly in headroom/proxy/handlers/openai.py across chat completion and websocket paths, allowing any client to imperson...

EUVD-2026-63905

Headroom's LLM proxy derives the memory owner from the x-headroom-user-id request header. The header is read directly at several points in headroom/proxy/handlers/openai.py, including the chat completion and websocket paths, and nothing binds the value to the caller. A client can therefore name...

CVE-2026-75110 MemOS Authentication Bypass via Unset INTERNAL_SERVICE_SECRET

MemOS is a memory operating system for LLMs and AI agents. In deployments where authentication is enabled AUTHENABLED=true but the undocumented, defaultless INTERNALSERVICESECRET environment variable is unset, the isinternalrequest check in src/memos/api/middleware/auth.py fails open:...

CVE-2026-19282 andreahaku llm_memory_mcp GitHooksManager.ts auto.capture command injection

A weakness has been identified in andreahaku llmmemorymcp up to f11dc8bcff3ff8cf943a2945f99ff3b0bdc8a6d0. This impacts the function auto.capture of the file src/autolearn/GitHooksManager.ts of the component llmmemorymcp. Executing a manipulation of the argument hash can lead to command injection...

CVE-2025-46560

CVE-2025-46560 affects vLLM 0.8.0–0.8.4, where the multimodal tokenizer’s input preprocessing uses placeholder tokens replaced by repeated tokens. The replacement logic relies on inefficient list concatenation, yielding quadratic time complexity (O(n²)) and enabling resource exhaustion via crafte...