Hold Guardrail Defense archived
Rebuff
Rebuff is an open-source prompt injection detector for AI applications that combines heuristics, an LLM-based classifier, a vector store of past attack embeddings, and canary-word leak detection. Intended for developers securing LLM apps; it also offers a hosted playground and a self-hostable server.
Unmaintained, superseded or risky; avoid new adoption.
Facts
- Repository
- protectai/rebuff
- Homepage
- github.com
- Listed via
- Curated
- First seen
- 2026-11-08
- License
- Apache-2.0
- Stars
- 1,532
- Last commit
- 2024-08-07
- Latest release
- v0.1.1 · 2024-01-20
- Checked
- 2026-11-13
Techniques
Listing is not endorsement. Summaries and notes are AI-assisted and reviewed; repository facts refresh automatically.