PentestGPT

Evals

Tool (not an eval — tooling/reference entry)

Autonomous pentest agent; one of the most popular in the category.

Category
Cyber offense capability
Insurance exposure
Breach/cyber
Publisher
NTU / academic
Publisher type
Academic
License
MIT
Status
Maintained (<12mo)
Last commit
2026-07-14
Stars
15962

View source on GitHub →


Wanich Risk Lab, 2026.