mishabar410/PolicyShield
Declarative firewall for OpenClaw tool calls.
This project helps operations engineers, security professionals, or anyone managing AI agents to prevent unwanted actions. It allows you to define safety rules in a simple YAML file to control what tools an AI agent can use or what data it can send. The system takes these rules and the AI's intended actions as input, then either blocks the action, redacts sensitive information, or requests human approval before the action is executed.
Available on PyPI.
Use this if you need to safely deploy AI agents for tasks like customer support or data processing, ensuring they don't misuse tools, leak sensitive data, or incur unexpected costs.
Not ideal if your AI agent's actions don't involve external tool calls or data interactions that need strict real-time oversight.
Stars
14
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/mishabar410/PolicyShield"
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