LLM Heist: Hijacking LiteLLM for Traffic Interception, Key Theft, and Tool-Call Injection
Summary
LiteLLM is an AI gateway (a proxy that provides unified access to multiple LLM providers while keeping API keys secure on the server side) that has become a high-value target for attackers. An attacker who gains the master admin credential can redirect traffic through a malicious gateway to steal API keys, intercept data, forge responses, or inject unauthorized tool calls, all while evading detection. The research describes attack techniques that red teams can use to test these vulnerabilities, noting that unpatched instances and exposed credentials are the primary entry points for this type of compromise.
Classification
Affected Vendors
Related Issues
CVE-2026-63086: text-generation-inference through 3.3.7 contains a server-side request forgery (SSRF) vulnerability in the OpenAI-compat
CVE-2026-34371: LibreChat is a ChatGPT clone with additional features. Prior to 0.8.4, LibreChat trusts the name field returned by the e
Original source: https://embracethered.com/blog/posts/2026/hijacking-litellm-for-fun-and-profit/
First tracked: August 3, 2026 at 02:01 PM
Classified by LLM (prompt v3) · confidence: 92%