agentleFS
sd0xdevsd0xdev/sd0x-harness/skills/dep-audit/SKILL.md

dep-audit

Skill192 starsChanged 37 days agoMITView on GitHub

Audit dependency security risks

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

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use Glob to check if .claude/scripts/dep-audit.sh exists in the project root.

    line 40
  2. Distinctive:

    If script succeeds, use its output and skip to the Output section.

    line 43
  3. Distinctive:

    If script fails, treat as a real audit failure (do not silently fallback).

    line 44
  4. Very specific:

    Default {LEVEL} is moderate unless --level argument is provided.

    line 63
  5. Very specific:

    If --fix is specified, run the fix command for the detected ecosystem after audit.

    line 65
  6. Distinctive:

    If no recognized manifest file exists, report an error.

    line 66

“Common” is measured: kept by at least 6 in 10 of the 8 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

Trigger

  • Keywords: dep audit, dependency audit, security audit dependencies, dep-audit

When NOT to Use

  • OWASP code review (use /codex-security)
  • Code review (use /codex-review-fast)
  • General security review (use /codex-security)

Workflow Steps

StepGoalSafety
auditScan dependencies for vulnerabilitiesread-only

Failure behavior: report-all

Task

Arguments

$ARGUMENTS
  • --level <severity> — Minimum reporting level (low/moderate/high/critical), default: moderate
  • --fix — Attempt automatic fix

Step 1: Check for audit script

Use Glob to check if .claude/scripts/dep-audit.sh exists in the project root.

  • Found → run: bash .claude/scripts/dep-audit.sh $ARGUMENTS
    • If script succeeds, use its output and skip to the Output section.
    • If script fails, treat as a real audit failure (do not silently fallback).
  • NOT found → skip to Step 2 (do NOT attempt to run the script).

Step 2: Fallback (no audit script)

Detect the project ecosystem and run the audit manually.

Ecosystem detection (check project root for manifest files):

ManifestEcosystemAudit CommandFix Command
package.json + pnpm-lock.yamlNode (pnpm)pnpm audit --audit-level {LEVEL}pnpm audit --fix
package.json + yarn.lockNode (yarn)yarn audit --level {LEVEL}yarn audit --fix or npx yarn-audit-fix
package.jsonNode (npm)npm audit --audit-level={LEVEL}npm audit fix
pyproject.tomlPythonpip-audit or safety checkpip-audit --fix
Cargo.tomlRustcargo auditcargo audit fix
go.modGogovulncheck ./...(manual fix)
build.gradleJava./gradlew dependencyCheckAnalyze(manual fix)

Default {LEVEL} is moderate unless --level argument is provided.

If --fix is specified, run the fix command for the detected ecosystem after audit. If no recognized manifest file exists, report an error.

Output

## Audit Results

| Severity | Count |
|----------|-------|
| Critical | 0 |
| High | 0 |
| Moderate | 0 |
| Low | 0 |

## Vulnerability Details

### [severity] Issue Title

- **Package**: package-name
- **Fix**: Available / Not available

## Gate

✅ **PASS** — No moderate or above vulnerabilities
❌ **FAIL** — Found high severity vulnerabilities

Examples

/dep-audit
/dep-audit --level high
/dep-audit --fix

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.