1. Vet at install
A tiny meta-skill sits in your agent. Every skill or MCP server install is checked before it runs. Warn, block, or allow by policy.
Install the CLI →KillerSkills checks every agent skill and MCP server at install time, runs it in a honeypot, and tells you what it actually did. Free in your agent. Governed for your company.
A tiny meta-skill sits in your agent. Every skill or MCP server install is checked before it runs. Warn, block, or allow by policy.
Install the CLI →Every skill runs inside a sandboxed agent with fake credentials, decoy tools, and a watched MEMORY.md. The verdict is a behavior trace, not a guess.
Read a verdict →53% of adopted skills are never updated while their upstreams change. We diff every release, re-detonate, and alert your team when a verdict moves.
See drift alerts →Every public skill on skills.sh, ClawHub, and the MCP registries, continuously re-scanned. Every verdict has a permanent page.
Browse all skills →See every skill and MCP server installed across the company, enforce an allow-list from the install hook, and get an audit trail your compliance team will accept.