Skip to content
TrustedSkillsbeta
Back to all skills

Claude Plugin Audit

Checked
outfitter-dev·vlatest·ai-ml·MIT

Analyzes Claude plugin interactions to identify potential security risks, data privacy concerns, and unexpected behavior.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add outfitter-dev/agents --skill claude-plugin-audit -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

outfitter-dev

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned outfitter-dev/agents at d37fffdd50.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
d37fffdd50
Manifest
plugins/outfitter/skills/claude-plugin-audit/SKILL.md
Scanned
1 file, 139 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill, claude-plugin-audit, provides auditing capabilities within Claude. It allows users to examine and understand the actions taken by Claude plugins. This includes reviewing plugin calls, parameters used, and responses received, providing transparency into plugin behavior.

When to use it

  • Debugging Plugin Interactions: Investigate unexpected results or errors when using Claude plugins.
  • Understanding Plugin Behavior: Gain insight into how a specific plugin is functioning and what data it's accessing.
  • Security Auditing: Review plugin calls for potential security vulnerabilities or privacy concerns.
  • Compliance Monitoring: Ensure plugin usage adheres to internal policies and regulatory requirements.

Key capabilities

  • Plugin call examination
  • Parameter review of plugin requests
  • Response analysis from plugins

Example prompts

  • "Show me the last 5 calls made to the [plugin name] plugin."
  • "What parameters were used in the most recent request to the [plugin name] plugin?"
  • “Audit my interactions with the [plugin name] plugin over the past hour.”

Tips & gotchas

The effectiveness of this skill depends on proper logging and instrumentation within the Claude plugins themselves. Without adequate logging, the audit trail will be limited.