hackingBuddyGPT

Framework / harness (not an eval — tooling/reference entry)

Framework for building LLM security-testing agents.

Category

Cyber offense capability

Insurance exposure

Breach/cyber

Publisher

TU Wien (IPA Lab)

Publisher type

Academic

License

MIT

Status

Active (<90d)

Last commit

2026-10-01

Stars

1273

View source on GitHub →

Wanich Risk Lab, 2026.