Preliminary research

LLM Heist: auditing LiteLLM traffic rerouting, provider-key exposure and tool-call injection

Johann Rehberger · Embrace The Red · 3 August 2026

AI-collected research leads through 6 October 2026, including bounded month-by-month reviews of selected social and community sources from January through September. Unranked, incomplete, not community-vetted, and subject to change.

Shows how an administrator credential can reroute a trusted LiteLLM gateway to an attacker proxy, causing provider credentials to be presented there. Subsequent forwarding and structured response modification enable traffic interception and tool-call injection, subject to the client’s tool permissions.

Record

Researcher

Johann Rehberger

Published by

Embrace The Red

Date

3 August 2026

In the archive

• Collected in the 2026 preliminary research sweep

Tags

• llm
• ai-agent
• proxy
• info-leak
• attack-chain
• case-study

This page is the archive's own catalogue record. The research is the work of Johann Rehberger, first published at the original source. Preserved copies are kept so the citation survives its host.