Blog
Writing about AI security, agentic pentesting, and the vulnerabilities we find.
-
Why I Built pwnkit
From 7 CVEs and manual pentesting to autonomous AI agents that re-exploit every finding to kill false positives.
-
How AI Agents Found 7 CVEs in Popular npm Packages
A systematic workflow using Claude Opus to audit open-source packages led to 73 findings, 7 published CVEs, and 40M+ weekly downloads affected.
-
The Age of Agentic Security
If AI agents can write 1,000 pull requests a week, AI agents should be testing 1,000 pull requests a week. The asymmetry is about to collapse.