agentleFS
roborracleroborracle/agent-workflow-kit/skills/dep-audit/SKILL.md

dep-audit

Skill0 starsChanged 3 months agoMITView on GitHub

Audit project dependencies for security vulnerabilities, outdated packages, and license compliance (check dependencies, security audit, are packages outdated).

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If audit scope includes "licenses":

    line 50

“Common” is measured: kept by at least 6 in 10 of the 9 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

Dependency Audit

Pre-fetched State

Package Manager Detection

!ls package.json composer.json requirements.txt Pipfile pyproject.toml Cargo.toml go.mod 2>/dev/null || echo "No package manager files found"

Node Security Audit

!npm audit --json 2>/dev/null | jq '{vulnerabilities: .metadata.vulnerabilities, total: .metadata.totalDependencies}' 2>/dev/null || echo "Not a Node project or npm not available"

Node Outdated

!npm outdated --json 2>/dev/null | jq 'to_entries | map({name: .key, current: .value.current, wanted: .value.wanted, latest: .value.latest}) | .[:20]' 2>/dev/null || echo "Not a Node project"

PHP Security Audit

!composer audit --format=json 2>/dev/null || echo "Not a PHP project"

PHP Outdated

!composer outdated --direct --format=json 2>/dev/null || echo "Not a PHP project"


Your Task

Audit scope: $ARGUMENTS (blank = all)

1. Security Vulnerabilities

  • Parse audit results from pre-fetched data
  • Categorize by severity: critical, high, moderate, low
  • For each critical/high vulnerability, provide:
    • Package name and affected version
    • Vulnerability description
    • Fix: npm audit fix or specific version update command

2. Outdated Dependencies

  • Flag packages more than 2 major versions behind
  • Flag packages with known EOL dates
  • Prioritize updates by: security fixes > major features > minor updates

3. License Compliance

If audit scope includes "licenses":

npx license-checker --summary 2>/dev/null || echo "license-checker not available"
  • Flag any GPL/AGPL in commercial projects
  • Flag any unknown licenses

4. Generate Report

DEPENDENCY HEALTH: [HEALTHY | WARNING | CRITICAL]

Security:
  Critical: X vulnerabilities
  High: X vulnerabilities
  Moderate: X vulnerabilities

Outdated:
  Major updates available: X packages
  Minor/patch updates: X packages

Action Items:
1. [Most urgent — critical security fixes]
2. [High priority — security + major updates]
3. [Routine — minor updates]

Quick Fix:
[Exact commands to resolve critical issues]

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.