CVE-2026-77776

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-2026-77776 Headroom Proxy Treats the Client-Supplied x-headroom-user-id Header as an Authenticated Identity

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...

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-2026-49468

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from...

PT-2026-50152

Name of the Vulnerable Software and Affected Versions LiteLLM versions prior to 1.84.0 Description A Host-header parsing flaw in the LiteLLM proxy allows unauthenticated access to protected management routes. The authentication layer derives the effective route from request.url.path in the get...

CVE-2026-42271

A flaw was found in LiteLLM, a proxy server AI Gateway for Large Language Model LLM APIs. Two endpoints, used for previewing an MCP server before saving it, accepted a full server configuration including command execution parameters. An authenticated user, even with low-privilege internal-user...

PT-2026-45209

Name of the Vulnerable Software and Affected Versions The product name cannot be determined. affected versions not specified Description An out-of-bounds read can occur in the iavb parse key data function within avb rsa.c due to improper input validation. This issue allows for local information...

CVE-2026-42208

LiteLLM proxy (AI Gateway) versions 1.81.16–1.83.6 suffer a SQL injection in the proxy API key verification path where the caller-supplied key is interpolated into a SQL query during error handling. An unauthenticated attacker can send a crafted Authorization header to LLM routes (e.g., POST /cha...

Embedded Malicious Code

Overview Affected versions of this package are vulnerable to Embedded Malicious Code that target Kubernetes environments by install a full LLM proxy service on the victim's machine, allowing the attacker to route LLM traffic through the compromised server. Remediation Avoid using kube-node-health...