{"skill":{"slug":"apoer-agent-guardrail","displayName":"APort Agent Guardrail","summary":"Pre-action authorization for AI agents. Verifies permissions before every tool runs (shell, messaging, git, MCP, data export). Works with OpenClaw, IronClaw,...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":59,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1771324443909,"updatedAt":1778559231028},"latestVersion":{"version":"1.0.0","createdAt":1771324443909,"changelog":"Initial release of aport-guardrail: pre-action authorization for AI agents.\n\n- Enforces deterministic, policy-based tool authorization for OpenClaw, IronClaw, and PicoClaw agents before every tool call.\n- Installer sets up config, plugin, and necessary script wrappers for automatic enforcement.\n- Supports both local and hosted (API) passports; integrates with APort policy engine.\n- Designed to be fail-closed, audit-ready, and impossible for agents to bypass.\n- CLI and direct script call documentation provided; supports shell, messaging, git, MCP, and data export tools.","license":null},"metadata":{"os":null,"systems":null},"owner":{"handle":"uchibeke","userId":"s17b2vmmny6282ekgb026j4vbx83gcw7","displayName":"Uchi Uchibeke","image":"https://avatars.githubusercontent.com/u/5677552?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1778559231028}}