prompt-shield

Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations. Maintained by mthamil107 on GitHub, where it has earned 10 stars from the community.

It's actively developed around agentic-ai, ai-safety, benchmarks, and is a solid reference for anyone building with these tools.