PandaGuard

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

Systematic jailbreak attack/defense evaluation with leaderboard.

Category

Jailbreak & misuse

Insurance exposure

Regulatory/bias

Publisher

Beijing AI Safety Institute

Publisher type

Government / standards body

License

MIT

Status

Maintained (<12mo)

Last commit

2026-03-23

Stars

69

View source on GitHub →

Wanich Risk Lab, 2026.