Definition
Agentic vulnerability discovery is the use of AI agents to autonomously find security bugs in software: reading code, running fuzzers, crafting inputs, and verifying exploits with little human steering. It’s a dual-use capability — useful for defenders auditing their own code, and worrying when offensive actors get it first.
Episodes covering this
Worth reading next
Papers we haven't done a deep dive on yet, but would recommend on this topic.