Tool Guard

Allowlist/denylist for AI agent tool calls with approval gates for destructive operations. Define which tools the agent can use freely, which require confirmation, and which are blocked entirely. Combines LOCO-Agent's resource authorization with Flare's anomaly-aware security heuristics. Trigger phrases: "restrict tools", "tool permissions", "block bash", "approval gate", "limit what you can do", "tool whitelist", "tool blacklist".

ArielSmoliar Updated
safe-agent - Security skills that make AI agents safe to run

File contents

ArielSmoliar/safe-agent commit 616e9c0b2a

Frequently asked questions

npx get-skill add arielsmoliar/tool-guard