Rebuff

Evals

Tool (not an eval — tooling/reference entry)

Prompt injection detector.

Category
Guardrails & safety classifiers (adjacent)
Insurance exposure
Prompt injection
Publisher
Protect AI
Publisher type
Company (open source)
License
Apache-2.0
Status
Stale (>12mo)
Last commit
2024-08-07
Stars
1529
Notes
Stale.

View source on GitHub →

Wanich Risk Lab, 2026.