AI agent security: taxonomy, status, and future

Dec. 2024


In the following google doc., we categorize and summarize recent papers on the security risks of LLM-enabled AI agents. It also contains interesting blogs and CVEs about real-world attacks. It includes benchmarks, attacks, and defenses. We use this doc. as a literature review and a paper tracker. We also provide potential research directions.

LLM-enabled agent systems safety and security