← Back to feed

AgentLeak – open-source privacy testing for multi-agent LLM systems

AI · Security · 2026-11-13 01:36

AgentLeak is an open-source tool designed to detect privacy leaks in multi-agent LLM systems by evaluating data security during inter-agent interactions. The current article body consists solely of GitHub navigation information, indicating the project's early stage or limited documentation availability.

Source: github.com


Auto-generated summary for reference only. RSS