llm-agent-testbed

🛡️ LLM Agent Security Testbed Empirical Vulnerability & Defense Harness for Tool-Calling LLM Agents A disciplined security testbed testing whether tool-equipped LLM agents can be manipulated into unauthorized data exfiltration via prompt injection, role-claim social engineering, and confused-deput...

Security Considerations for Multi-Agent Systems

Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct security vulnerabilities from those documented for singular AI...