AgentGuard - Scan AI agent Skills for risks before you install them

Hey Product Hunt 👋 I’m launching AgentGuard — a free scanner for AI agent Skills (SKILL.md). As more people install Skills into coding agents, it’s hard to know what those Skills can actually do: shell access, network calls, secret access, vague instructions, etc. AgentGuard lets you: 1. Paste a SKILL.md 2. Run security + quality analysis 3. Get a Trust Report with scores, capabilities, findings, and a verdict It’s free, no account required. Automated analysis can’t guarantee absolute safety — it helps you make a more informed install decision. I’d love feedback on: – Is the Trust Report clear enough? – What’s missing for your Skill-review workflow? – Would GitHub URL / CLI scanning be useful next? Thanks for checking it out.