本文へ移動
cccskills
無料GitHub で公開

ln-625-dependencies-auditor

Checks outdated packages, unused deps, reinvented wheels, vulnerability scan (CVE/CVSS). Supports mode: full | vulnerabilities_only.

インストール方法を見る

含まれるファイル(3)

  • SKILL.md6.8 KB
  • references/ci_integration_guide.md2.9 KB
  • references/vulnerability_commands.md2.8 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

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  • Check outdated packages, unused deps, wheel reinvention, CVE vulnerabilities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

ParamValuesDefaultDescription
modefull / vulnerabilities_onlyfullfull = all 5 checks, vulnerabilities_only = only CVE scan

Inputs (from Coordinator)

MANDATORY READ: Load shared/references/audit_worker_core_contract.md.

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

MANDATORY READ: Load shared/references/two_layer_detection.md for detection methodology.

  1. Parse context + mode parameter + output_dir
  2. Run dependency checks (Layer 1: audit tools, based on mode)
  3. Analyze context per candidate (Layer 2):
    • Available Features: read usage — is lodash used for 1 function (easy replace) or deeply integrated (hard)?
    • Custom Implementations: read code — truly reimplementing a library, or domain-specific logic?
    • Vulnerability: read code — is the vulnerable API actually called in this project?
  4. Collect findings
  5. Calculate score
  6. 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
  7. 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 Outdated Packages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  • Run npm outdated --json (Node.js)
  • Run pip list --outdated --format=json (Python)
  • Run cargo outdated --format=json (Rust)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_worker_core_contract.md and shared/references/audit_scoring.md.

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

Output Format

MANDATORY READ: Load shared/references/audit_worker_core_contract.md and shared/templates/audit_worker_report_template.md.

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

FilePurpose
references/vulnerability_commands.mdEcosystem-specific audit commands
references/ci_integration_guide.mdCI/CD integration guidance
shared/references/cvss_severity_mapping.mdCVSS to severity level mapping
shared/references/audit_output_schema.mdAudit output schema

Critical Rules

MANDATORY READ: Load shared/references/audit_worker_core_contract.md.

  • 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

MANDATORY READ: Load shared/references/audit_worker_core_contract.md.

  • 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

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

Whole site or product — a full web accessibility (a11y) audit against WCAG 2.2, following the WCAG-EM methodology. Defines scope, samples representative pages and flows, runs the automated tier (`accessibility-scan`) and the hands-on manual tier (`accessibility-inspect`), and produces one conformance report. Grades each finding by severity and evidence basis, and states per-criterion conformance as pass, fail, or undetermined (needs a human). Use it for 'audit my site for accessibility', 'is this product accessible', 'a11y audit', 'WCAG or Section 508 conformance report', or any multi-page assessment. Assesses; does not fix (use `accessibility-fix`) or diff (use `accessibility-diff`). For a single page use `accessibility-scan`; for hands-on keyboard and screen-reader checks use `accessibility-inspect`.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

Regression check — diff a live page's web accessibility (a11y) violations against a baseline. By default it compares your uncommitted changes (stash-based); pass `--branch [<name>]` to compare against a branch. Reports the new WCAG violations introduced, the ones fixed, and the count of pre-existing ones. Use it for 'did my change break accessibility', 'what a11y issues did this PR add', or as a CI gate. For a full scan of one page use `accessibility-scan`; for a whole site use `accessibility-audit`.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

Remediation only — repair web accessibility (a11y) violations against WCAG 2.2 with a baseline, edit, and verify loop. Takes a target (URL, files, directory) or a findings worklist from `accessibility-scan`/`accessibility-inspect`/`accessibility-audit`, applies mechanical fixes as given, leaves TODOs for visual or contextual judgment, and verifies by re-running the baseline check. It only fixes. To find issues use `accessibility-scan` (one page, automated), `accessibility-inspect` (one page, manual), or `accessibility-audit` (whole site, WCAG-EM); to check for regressions use `accessibility-diff`. Use it for 'fix the a11y issues in X', 'make this accessible', 'add missing alt text and labels', 'apply these accessibility fixes', 'remediate these violations'.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

One page, hands-on manual tier — drive a live page through the web accessibility (a11y) checks a rule engine can't decide: keyboard operation and focus order, screen-reader names, roles and states from the accessibility tree, reflow and zoom, reduced motion, form errors, and target size. Grades each finding by evidence basis (verified / confirm-with-a-human / human-required) and severity, and closes every criterion in a ledger: verified, flagged, not exercised, or N/A. Locates and assesses; does not fix (use `accessibility-fix`). Use it for keyboard testing, focus-order checks, screen-reader or a11y-tree review, reflow and zoom at 200%, or 'is this operable, not just lint-clean'. The automated tier is `accessibility-scan`; `accessibility-audit` runs both across a sampled site.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

One page, automated tier — run the web accessibility (a11y) rule engine against a live page and locate every violation it can detect mechanically. Pass a URL, a config target name (e.g. `accesslint:accessibility-scan dev`), or nothing to use the default target from `accesslint.config.json`. Ensures a debuggable Chrome, runs the @accesslint/core engine over CDP, and returns a worklist of live-DOM WCAG 2.2 violations, each grounded to its DOM selector and source `file:line`. Locates; doesn't edit. Use it for 'is this page accessible', 'check a11y on this URL', 'find contrast and alt-text issues', or to verify a UI change. For hands-on keyboard and screen-reader checks use `accessibility-inspect`; for a whole site or product use `accessibility-audit`; to diff against uncommitted changes or a branch use `accessibility-diff`.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

tensology のスキルをすべて見る

このスキルの問題を報告する