[ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".
Repository Index
47,133 repositories indexed
25–31 of 31 · Most stars
Tom's Honey Pot as seen in Applied Network Security Monitoring.
A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set the plan in motion. The agents take a prompt, and each iteration must update specs and commit through guardrails.
Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.
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.
- agentic-ai
- ai-safety
- fastapi
- langchain
3-level override system for Claude Code - prevents destructive system operations. Born from a real incident.
Autonomous agent operational guardrails for Gemini CLI