Skip to content

Check an AI skill before you install it.

A skill is a set of instructions and code your agent will follow. Point Aevrin at one and it reads both. Then it tells you: Safe, Caution or Do not install.

Start freeRead the docs
Why it matters

The problem Skill Inspector solves.

Your agent follows a skill with your permissions. One sentence in a SKILL.md file can steer the agent somewhere else. One helper script can read your keys. A skill needs the same care as any package you install.

  1. 1

    Read it

  2. 2

    Score the risk

  3. 3

    Tell you what to do

What goes in

  • A Git repository or web address
  • A ZIP file
  • A folder on your computer
  • SKILL.md files
  • The skill's details
  • Its libraries

What comes back

  • A risk score and how serious it is
  • Safe, Caution or Do not install
  • Hidden instructions it found
  • Ways it could send your data out
  • Risky libraries
  • Reports as SARIF, JSON and Markdown

Why you can trust what it says.

  • Reads the words too

    A trick can hide in plain sentences, not just in code. Aevrin reads what the skill tells your agent to do, next to what its scripts really do.

  • Checks in layers

    Code checks, security rules and a lookup of known library bugs run first. An optional AI pass then reads for intent that rules cannot see.

  • Reports where you work

    SARIF for code scanning, JSON for scripts, Markdown for a pull request, and a short summary in your terminal.

Part of Aevrin MCP

The other five checks.

Put Skill Inspector to work.

Start on the free plan. No card, and nothing renews on its own. Or add Aevrin MCP and use it from your agent.

Start freeSet up Aevrin MCP