logo

Hackers Actively Scan LiteLLM AI Servers for Critical Flaws Enabling RCE Attacks

ID: ad805b65-b5f8-53fa-b2cc-98fe533534a1

STIX ID: report--ad805b65-b5f8-53fa-b2cc-98fe533534a1

Feed Name: cybersecurityNews.com

Threat Score
80/100

Date Published: 2026-11-20

Date Updated: 2026-11-20

Author: Tushar Subhra Dutta

...
...

Researchers observed active internet scanning of LiteLLM AI gateways exploiting two chained flaws — a command-execution weakness in LiteLLM's MCP test endpoint (CVE-2026-42271) and a Host header validation bypass in Starlette (CVE-2026-48710) — to obtain remote code execution without valid login; the report includes observed requests, IoCs (paths, Host header anomalies, User-Agent, payload), measured exposure, and remediation steps (upgrade LiteLLM and Starlette, restrict public access, rotate keys).

Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.