1.mthamil107 / prompt-shieldPrompt-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.agentic-aiai-safetyfastapilangchainllm-firewallllm-security+14 morePythonAPACHE-2.019 total9 forks+3 starsfrom 16 · score 1.39