Vulnerability  ·  2026-06-18

LiteLLM MCP Endpoint Command Injection — Unauthenticated RCE via Starlette BadHost Chain (CISA KEV)

VulnerabilityHigh impactGlobalCVE-2026-42271
CISA added CVE-2026-42271 to its Known Exploited Vulnerabilities catalog on June 9, 2026, confirming active in-the-wild exploitation. The flaw resides in two MCP server preview endpoints in LiteLLM that accept full server configurations — including command, args, and env fields — and spawn the supplied command as a subprocess with no validation or sandboxing. Chained with CVE-2026-48710, a host-header parsing flaw in Starlette (the ASGI framework underpinning LiteLLM, vLLM, and many FastAPI-based AI tools), the authenticated requirement is bypassed entirely, yielding unauthenticated RCE. Horizon3.ai published a full working proof-of-concept. CISA characterized the pattern as 'sustained targeting of AI gateway infrastructure.'
LiteLLM is the central key-management and routing chokepoint for enterprise AI deployments. Compromise exposes every configured provider credential (OpenAI, Anthropic, Azure, AWS Bedrock, etc.), all prompt and response data (including PII, source code, and pasted secrets), and — critically — allows silent tampering of model responses in transit to downstream AI agents. A gateway-level compromise converts the attacker into the steering mechanism for every agent routed through it. CVE-2026-48710 also affects vLLM and any other ASGI app using path-based auth with Starlette ≤1.0.0, widening the blast radius significantly.
Attacker sends a crafted POST to /mcp-rest/test/connection or /mcp-rest/test/tools/list with a malicious stdio MCP server config (command/args/env fields). LiteLLM spawns the supplied command as a subprocess on the host with no sandbox. Chained with CVE-2026-48710 (Starlette 'BadHost' host-header bypass), authentication is skipped entirely — unauthenticated RCE from the network. Horizon3.ai published a working PoC demonstrating the full chain.
BerriAI LiteLLM 1.74.2 – 1.83.6; Starlette 0.8.3 – 1.0.0
Upgrade LiteLLM to ≥1.83.7 and Starlette to ≥1.0.1. Rotate all provider keys, master key, and database credentials if previously exposed. Restrict MCP test endpoints to PROXY_ADMIN role. CISA KEV federal deadline was June 22, 2026.
Sources
Vulert / NVD — CVE-2026-42271 technical deep-dive (verified full text)avinashsangle.com — LiteLLM CVE-2026-42271 + CVE-2026-48710 chain (verified full text)TechRepublic — CISA KEV Warning: LiteLLM AI Gateway Flaw (verified full text)CISA KEV Catalog
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →