Preliminary research

OffGuard: LiteLLM authentication and proxy-boundary case study

Breaking LiteLLM: From Auth Bypass to Cloud Compromise

Amitai Cohen and Yaara Shriki · wiz.io · 9 September 2026

AI-collected research leads through 22 September 2026, including targeted additions between broader sweeps. Unranked, incomplete, not community-vetted, and subject to change.

Explains separate LiteLLM failures in MCP authentication, custom guardrails and administrative defaults. The article distinguishes unauthenticated MCP access from guardrail execution that requires administrative access, and describes the configuration-dependent impact.

Record

Document

Breaking LiteLLM: From Auth Bypass to Cloud Compromise

Researcher

Amitai Cohen and Yaara Shriki

Published by

wiz.io

Date

9 September 2026

Topic

HTTP

In the archive

• Collected in the 2026 preliminary research sweep

Related sources

• OffGuard: Breaking the Most Popular AI Gateway from Auth Bypass to Cloud Compromise Whitepaper

Tags

• auth-bypass
• ai-agent
• mcp
• sandbox-escape
• owasp-a01-2021

This page is the archive's own catalogue record. The research is the work of Amitai Cohen and Yaara Shriki, first published at the original source. Preserved copies are kept so the citation survives its host; this one was last captured on 18 September 2026.