Dependencies Auditor (L3)

VerifiedSafe

Specialized worker auditing dependencies, detecting outdated packages, unused deps, reinvented wheels, and CVE vulnerabilities. Modes: full or vulnerabilities_only.

Sby Skills Guide Bot
SecurityIntermediate
3/2/2026
Claude Code
#dependencies#vulnerability-scan#cve#code-audit#package-management

Recommended for

Automated summary

Audit worker that inspects a project's dependencies: outdated packages, unused dependencies, reinvented wheels, hand-rolled implementations, and CVE/CVSS vulnerabilities, producing a compliance score out of 10.

Strengths

  • Covers five distinct checks (outdated packages, unused dependencies, unused native features, custom implementations, CVEs)
  • Maps vulnerabilities to CVSS severity bands with per-severity remediation timeframes
  • Detects multiple ecosystems (npm, pip, Cargo, NuGet, Go, Bundler, Composer)
  • Offers a `vulnerabilities_only` mode that plugs into a security-setup pipeline

Limitations

  • Depends on external tooling (`npm outdated`, `pip list --outdated`, `cargo outdated`, audit commands) being installed and runnable
  • Grep-based unused-dependency detection can yield false positives (dynamic imports, config-only usage)
  • Designed as a worker inside a coordinator pipeline (ln-620 / ln-760) and expects a `contextStore` plus `output_dir`
When to use it

Use it to audit a repository's dependency hygiene or to run a focused CVE scan before a release.

When not to use it

Avoid it standalone on a project with no dependency manifest or audit tooling installed, or as a replacement for a dedicated SCA scanner in CI.

Security analysis

Safe
Quality score84/100

The skill is a read-only auditing worker. It only inspects manifests and runs standard package-manager audit/outdated commands, explicitly forbids auto-fixing or modifying manifests/lock files, and contains no destructive, exfiltration, or obfuscated behavior. Bash use is proportionate and legitimate, with only incidental network access from package managers, so overall risk is low.

Findings
  • •Runs Bash to execute package-manager commands (npm outdated, pip list --outdated, cargo outdated, ecosystem audit tools), which may contact remote registries (network access)
  • •References external shared/ and references/ files resolved relative to the skills repo root; content of those files is not shown and would need separate review
How this analysis is made

Examples

Full dependency audit
Audit the dependencies in this repo: list outdated packages, unused dependencies, places where a native API would replace a library, hand-rolled implementations, and any CVEs. Then give me a compliance score out of 10.
Vulnerability-only scan
Run a vulnerabilities-only dependency scan on this project and report every CRITICAL and HIGH CVE with the recommended fix priority.
Unused dependency cleanup
Check package.json for dependencies that are never imported anywhere in the codebase and tell me which ones I can safely remove.

name: ln-625-dependencies-auditor description: "Dependencies audit worker (L3). Checks outdated packages, unused deps, reinvented wheels, vulnerability scan (CVE/CVSS). Supports mode: full | vulnerabilities_only." allowed-tools: Read, Grep, Glob, Bash

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.

Dependencies & Reuse Auditor (L3 Worker)

Specialized worker auditing dependency management, code reuse, and security vulnerabilities.

Purpose & Scope

  • Worker in ln-620 coordinator pipeline (full audit mode)
  • Worker in ln-760 security-setup pipeline (vulnerabilities_only mode)
  • Audit dependencies and reuse (Categories 7+8: Medium Priority)
  • Check outdated packages, unused deps, wheel reinvention, CVE vulnerabilities
  • Calculate compliance score (X/10)

Parameters

| Param | Values | Default | Description | |-------|--------|---------|-------------| | mode | full / vulnerabilities_only | full | full = all 5 checks, vulnerabilities_only = only CVE scan |

Inputs (from Coordinator)

Receives contextStore with tech stack, package manifest paths, codebase root, output_dir.

From ln-620 (codebase-auditor): mode=full (default) From ln-760 (security-setup): mode=vulnerabilities_only

Workflow

  1. Parse context + mode parameter + output_dir
  2. Run dependency checks (based on mode)
  3. Collect findings
  4. Calculate score
  5. Write Report: Build full markdown report in memory per shared/templates/audit_worker_report_template.md, write to {output_dir}/625-dependencies.md in single Write call
  6. Return Summary: Return minimal summary to coordinator

Audit Rules (5 Checks)

1. Outdated Packages

Mode: full only

Detection:

  • Run npm outdated --json (Node.js)
  • Run pip list --outdated --format=json (Python)
  • Run cargo outdated --format=json (Rust)

Severity:

  • HIGH: Major version behind (security risk)
  • MEDIUM: Minor version behind
  • LOW: Patch version behind

Recommendation: Update to latest version, test for breaking changes

Effort: S-M (update version, run tests)

2. Unused Dependencies

Mode: full only

Detection:

  • Parse package.json/requirements.txt
  • Grep codebase for import/require statements
  • Find dependencies never imported

Severity:

  • MEDIUM: Unused production dependency (bloats bundle)
  • LOW: Unused dev dependency

Recommendation: Remove from package manifest

Effort: S (delete line, test)

3. Available Features Not Used

Mode: full only

Detection:

  • Check for axios when native fetch available (Node 18+)
  • Check for lodash when Array methods sufficient
  • Check for moment when Date.toLocaleString sufficient

Severity:

  • MEDIUM: Unnecessary dependency (increases bundle size)

Recommendation: Use native alternative

Effort: M (refactor code to use native API)

4. Custom Implementations

Mode: full only

Detection:

  • Grep for custom sorting algorithms
  • Check for hand-rolled validation (vs validator.js)
  • Find custom date parsing (vs date-fns/dayjs)

Severity:

  • HIGH: Custom crypto (security risk)
  • MEDIUM: Custom utilities with well-tested alternatives

Recommendation: Replace with established library

Effort: M (integrate library, replace calls)

5. Vulnerability Scan (CVE/CVSS)

Mode: full AND vulnerabilities_only

Detection:

  • Detect ecosystems: npm, NuGet, pip, Go, Bundler, Cargo, Composer
  • Run audit commands per references/vulnerability_commands.md
  • Parse results with CVSS mapping per shared/references/cvss_severity_mapping.md

Severity:

  • CRITICAL: CVSS 9.0-10.0 (immediate fix required)
  • HIGH: CVSS 7.0-8.9 (fix within 48h)
  • MEDIUM: CVSS 4.0-6.9 (fix within 1 week)
  • LOW: CVSS 0.1-3.9 (fix when convenient)

Fix Classification:

  • Patch update (x.x.Y) → safe auto-fix
  • Minor update (x.Y.0) → usually safe
  • Major update (Y.0.0) → manual review required
  • No fix available → document and monitor

Recommendation: Update to fixed version, verify lock file integrity

Effort: S-L (depends on breaking changes)


Scoring Algorithm

MANDATORY READ: Load shared/references/audit_scoring.md for unified scoring formula.

Note: When mode=vulnerabilities_only, score based only on vulnerability findings.

Output Format

MANDATORY READ: Load shared/templates/audit_worker_report_template.md for file format.

Write report to {output_dir}/625-dependencies.md with category: "Dependencies & Reuse" and checks: outdated_packages, unused_deps, available_natives, custom_implementations, vulnerability_scan.

Return summary to coordinator:

Report written: docs/project/.audit/ln-620/{YYYY-MM-DD}/625-dependencies.md
Score: X.X/10 | Issues: N (C:N H:N M:N L:N)

Reference Files

| File | Purpose | |------|---------| | shared/templates/audit_worker_report_template.md | Worker report file format | | references/vulnerability_commands.md | Ecosystem-specific audit commands | | references/ci_integration_guide.md | CI/CD integration guidance | | shared/references/cvss_severity_mapping.md | CVSS to severity level mapping | | shared/references/audit_scoring.md | Audit scoring formula | | shared/references/audit_output_schema.md | Audit output schema |

Critical Rules

  • Do not auto-fix: Report only, never modify package manifests or lock files
  • Mode-aware execution: In vulnerabilities_only mode, skip checks 1-4 entirely
  • Effort realism: S = <1h, M = 1-4h, L = >4h
  • CVSS-based severity: Map vulnerability severity strictly via shared/references/cvss_severity_mapping.md
  • Exclusions: Skip devDependencies for vulnerability severity escalation, skip vendored/bundled deps

Definition of Done

  • contextStore parsed (including mode parameter and output_dir)
  • All applicable checks completed (5 for full, 1 for vulnerabilities_only)
  • Findings collected with severity, location, effort, fix_type, recommendation
  • Score calculated per shared/references/audit_scoring.md
  • Report written to {output_dir}/625-dependencies.md (atomic single Write call)
  • Summary returned to coordinator

Version: 4.0.0 Last Updated: 2026-02-05

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/dependencies-auditor-l3-mm8o521b/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/dependencies-auditor-l3-mm8o521b' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/dependencies-auditor-l3-mm8o521b/download' --output '.skill-downloads/dependencies-auditor-l3-mm8o521b/SKILL.md.part' && mv '.skill-downloads/dependencies-auditor-l3-mm8o521b/SKILL.md.part' '.skill-downloads/dependencies-auditor-l3-mm8o521b/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Grep, Glob, Bash

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/dependencies-auditor-l3-mm8o521b/SKILL.md' && test -s '.skill-downloads/dependencies-auditor-l3-mm8o521b/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/ln-625-dependencies-auditor' && cp -R '.skill-downloads/dependencies-auditor-l3-mm8o521b' '.claude/skills/ln-625-dependencies-auditor'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/dependencies-auditor-l3-mm8o521b'

openskills read 'dependencies-auditor-l3-mm8o521b'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/dependencies-auditor-l3-mm8o521b/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills