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.
ClawShield is a security proxy designed for businesses and individuals using AI agents like Claude or GPT. It acts as a shield, inspecting all interactions with your AI to prevent sensitive data like PII or API keys from leaking out and to stop malicious prompt injection attacks. It also offers 5 specialized AI agents for various tasks and provides a dashboard for monitoring activity.
Use this if you are using AI agents and need to protect sensitive information, prevent 'jailbreak' attacks, and ensure your AI interactions are secure and compliant.
Not ideal if you are not using AI agents, do not handle sensitive information, or only use AI for non-critical, low-risk tasks.
Stars
98
Forks
11
Language
Go
License
Apache-2.0
Category
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.
Featured in
Higher-rated alternatives
23blocks-OS/ai-maestro
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph...
ImKKingshuk/LockKnife
LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI...
conorluddy/ios-simulator-skill
An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and...
backbay-labs/clawdstrike
Runtime security enforcement and threat hunting engine for autonomous AI fleets. Build Swarm...
FlineDev/ContextKit
Claude Code context engineering & planning system for individual AI development workflows