AgentLeak – open-source privacy testing for multi-agent LLM systems
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
AgentLeak is an open-source benchmark and Python toolkit from El Yagoubi, Badu-Marfo, and Al Mallah for testing privacy leakage in multi-agent LLM systems, covering channels such as tool calls, inter-agent messages, shared memory, and logs.