SleuthCo/clawshield-public

Security proxy for AI agents. Scans every message for prompt injection, PII, and secrets. Defense-in-depth: Go proxy + iptables firewall + eBPF kernel monitor. YAML policy engine, audit logging, 5 AI agents with RAG knowledge bases.

43
/ 100
Emerging

Integrates with OpenClaw gateway and Claude/GPT-compatible APIs through configurable OpenAI-compatible endpoints, while surfacing security decisions via Prometheus metrics and SQLite audit logs with forensic-grade decision explainability (rule IDs, match excerpts, confidence scores). Provides policy-as-code hot-reload via file-watch with atomic request isolation, plus real-time chunk-by-chunk scanning of SSE/NDJSON streams using sliding-window overlap to catch injection patterns spanning boundaries.

No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 11 / 25
Community 13 / 25

How are scores calculated?

Stars

98

Forks

11

Language

Go

License

Apache-2.0

Last pushed

Mar 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/SleuthCo/clawshield-public"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.