Skillet
Browse
⌘K
Log inJoin
BrowseDocs
Log in
docs
  • What is Skillet?
  • Summon a kit
  • Install
  • Add skills
  • Skills & kits
  • Approve updates
  • Publish a skill
  • Teams
  • Safety
  • Privacy
  • FAQ
  • API
  • CLI
  • MCP
  • Scanner
  • Skill.md
  • Versioning
  • What is Skillet?
  • Summon a kit
  • Install
  • Add skills
  • Skills & kits
  • Approve updates
  • Publish a skill
  • Teams
  • Safety
  • Privacy
  • FAQ
  • API
  • CLI
  • MCP
  • Scanner
  • Skill.md
  • Versioning

How Skillet scans a skill

Every published skill is scanned, and the results sit on its page. Here’s what the scan looks at, what it means, and how to read any skill’s trust panel.


What the scan checks

Skillet reads a skill’s files (its instructions and any bundled code) and matches them against patterns for risky capabilities and threats. It matches code and text, not intent, so false positives are common: an install command in the docs, a `system:` line in an AI-SDK example, a `DROP TABLE` in a best-practices note all look like their dangerous cousins. Treat a finding as something to check, not a verdict.

Confidence decides how loudly a finding shows. Skillet warns strongly when something is genuinely serious and simply informs when it isn’t, so the rare red warning stays meaningful. It never blocks an install; you keep the final call.

How findings are shown

Safety
A serious, high-confidence finding: a `rm -rf /`, a leaked key, a reverse shell. Shown in red, unmissable, but never blocking. You see the warning and decide.
Permissions
What the skill can do and access, listed plainly. Anything lower-confidence the scanner noticed (a documented install command, an injection-shaped line) shows here too, set apart, so you see everything without being alarmed.

A clean skill shows no Safety card at all, just its permissions. Wherever a finding lands, you can expand it to see the exact file and line it came from.

Permissions

What a skill can do: the capabilities Skillet detects, most-impactful first.

PermissionWhat it means
Run commandsRuns shell commands on your machine.
Use the internetConnects to the internet to fetch data or call other services.
Write filesCreates or changes files on disk.
Delete filesRemoves or overwrites files.
Read env variablesReads environment variables, which may hold tokens or keys.
Install packagesInstalls third-party packages, which can run their own setup scripts.
Connect an MCP serverWires up a Model Context Protocol server, whose tools then run with the agent’s access.
Run generated codeRuns code that it generates at runtime.
Add to your outputInserts its own content — like footers, credits, or links — into what the agent produces for you.

Flags

What gets checked: the threat patterns Skillet looks for. A high-confidence match shows in Safety; anything lower informs alongside the skill’s permissions.

FlagWhat it means
Prompt injectionText that could try to hijack an agent’s instructions.
Send data outMoves data to an outside destination. Confirm that’s expected.
Delete or overwrite filesRemoves or overwrites files. Destructive if the path is wrong.
Hard-to-read codeEncoded or scrambled content you can’t read at a glance.
Possible secretA value that looks like a password or key — it could be a real credential.
Ask for more accessRequests elevated permissions. Confirm the skill needs them.
Act without askingTakes actions on its own, like auto-approving or looping. Fine for trusted automation, worth a glance.
Reveal the system promptTries to reveal an agent’s hidden system instructions.
Fetch and run codeDownloads code or a package at runtime and runs it, so what executes can change later.
Act on model outputFeeds the model’s own output into a shell, query, or page without checking it first.
Inject promotional contentInstructs the agent to slip promotional links or branding into your deliverables.
Rewrite agent memoryWrites instructions into the agent’s memory that persist across sessions.
Disable a safety checkTurns off a guardrail like auth, TLS verification, or a confirmation prompt.
Persist or self-modifySets itself to run later or rewrites its own code to keep running.
Run a shell commandCalls exec, eval, or a subprocess to run a command directly.

Scanning is one guardrail. For the rest (approving other people’s updates, signing, and keeping your own skills private), see Safety

MCPSkill.md

On this page

  • What the scan checks
  • How findings are shown
  • Permissions
  • Flags
Skilletseasoned to taste
Get appStatsBlogDocs
    Star3