Agent And Tool Security: 2 curated resources
Curated material on agent and tool security within security and red teaming.
2 resources · page 1 of 1
The lethal trifecta for AI agents
A defensive framework for recognizing risky combinations of agent capabilities and untrusted inputs.
Design Patterns for Securing LLM Agents against Prompt Injections
Summary of a paper's defensive agent architectures.