agentleFS
Sign inStart free
trac3r00trac3r00/agent-skills/skills/skill-audit/SKILL.md

skill-audit

Skill0 starsChanged 3 months agoMITView on GitHub

Security-scans third-party agent skills before you trust them. A SKILL.md is executable authority — agents follow it with your credentials and filesystem. Detects prompt-injection patterns (instruction overrides, concealment directives), data-exfiltration signatures (sensitive paths + network sends), and dangerous script patterns (pipe-to-shell, eval-on-download) in any skills directory. Offline, deterministic, stdlib-only.

  • Pipes a download into a shell
  • Reads credentials

58 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use root-cause, write-a-skill and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Ingramradical235Skill

    root-cause

    Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.

    Also in 3 projects that use this

  • simo97Skill

    write-a-skill

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    reflect

    Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.

    Also in 5 projects that use this

  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 4 projects that use this

  • eherrerosjSkill

    humanize

    Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive 'Signs of AI writing' guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Triggers on: 'humanize', 'make this sound human', 'remove AI writing', 'de-AI', 'sound more natural', 'less robotic', 'too AI-sounding', or when reviewing text that reads like AI output.

    Also in 3 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 52 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every finding carries skill, file:line, and the evidence line.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 52 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill Audit

You audit npm packages before installing them. Skills deserve the same: a malicious SKILL.md does not need code execution — the agent IS the executor.

Commands

python3 scripts/skill_audit.py ~/.claude/skills ~/.codex/skills   # audit stores
python3 scripts/skill_audit.py --skill ./some-new-skill           # one skill
python3 scripts/skill_audit.py ~/.agents/skills --json --fail-over 0  # CI gate

Pair with skill-sync: after syncing skills into a universal directory, audit that directory before any agent reads it.

Detects

KindPattern
instruction-override"ignore previous instructions", "disregard system prompt"
concealment"do not tell the user", "without informing the owner"
sensitive-path-exfil~/.ssh, .env, credentials paths near curl/POST/fetch (same line or 3-line window)
pipe-to-shellcurl ... | sh install patterns
eval-on-downloadeval(urlopen(...)) and friends
credential-harvestenvironment dumps flowing into network sends
large-encoded-blob120+ char base64 payloads hiding instructions

Reading results

Every finding carries skill, file:line, and the evidence line. Legitimate skills trip patterns too (a browsing skill legitimately mentions curl and cookies) — that is why the default gate is --fail-over 0 findings for NEW skills you have not read, and a higher budget for stores you already reviewed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free