本文へ移動
cccskills
無料GitHub で公開

security

Scan dependencies and tracked files for known vulnerabilities and leaked secrets; fix what's fixable, report the rest. For reviewing a pending diff, prefer a platform security-review skill.

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。

インストール方法を見る

含まれるファイル(1)

  • SKILL.md4.3 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。

Security — Vulnerability Scanner & Secret Audit

You are a security engineer. Auto-detect package managers, scan for vulnerabilities and leaked secrets, fix what's fixable, report the rest.

Do NOT ask for permission — scan everything, fix what you can, report the rest.


Step 1 — Detect package managers

PROJECT_ROOT=$(git rev-parse --show-toplevel)
cd "$PROJECT_ROOT"
ls package.json api/package.json requirements.txt pyproject.toml 2>/dev/null

Step 2 — Load project-specific known exceptions

Read the project instruction file for any documented known exceptions before determining what is blocking:

# Detect project instruction file
INSTRUCTION_FILE=$(for f in CLAUDE.md AGENTS.md .cursorrules; do [ -f "$PROJECT_ROOT/$f" ] && echo "$PROJECT_ROOT/$f" && break; done)
[ -n "$INSTRUCTION_FILE" ] && grep -A3 -i "known exception\|security exception\|audit exception" "$INSTRUCTION_FILE" 2>/dev/null | head -30

In addition, the following patterns are universally non-blocking across all projects (install-time only, not runtime risks):

  • tar, node-gyp, @mapbox/node-pre-gyp, cacache, make-fetch-happen — native addon compilation during npm install
  • undici via Firebase SDK when fix requires --force (breaks Vite/other deps)
  • sqlite3 install-time compilation deps

Any high/critical vulnerability NOT matching the above patterns → BLOCKING.


Step 3 — Dependency vulnerability scan

npm projects:

# Root (frontend)
npm audit --json 2>/dev/null

# Backend (if api/ exists)
cd api && npm audit --json 2>/dev/null

Build severity summary per project:

ProjectCriticalHighModerateLowTotal

Detail each critical/high: package, severity, advisory title, fix available, dependency chain, exception status.

Python projects:

./venv/bin/pip-audit 2>/dev/null || (./venv/bin/pip install pip-audit && ./venv/bin/pip-audit)

Step 4 — Preview and apply safe fixes

npm:

npm audit fix --dry-run
npm audit fix          # NOT --force
cd api && npm audit fix

Python: upgrade specific packages in pyproject.toml, reinstall, re-audit.

Only critical/high require immediate fixing. Never use npm audit fix --force.


Step 5 — Secret scan

grep -rn "sk-proj-\|sk-ant-\|AKIA\|ghp_\|gho_\|AIza\|ya29\." \
  --include="*.ts" --include="*.tsx" --include="*.js" \
  --include="*.py" --include="*.json" \
  --include="*.yaml" --include="*.yml" --include="*.env*" \
  . | grep -v node_modules | grep -v venv | grep -v dist | grep -v ".claude/" \
  || echo "No secrets found"
  • Test fixtures with fake keys are acceptable — ignore them
  • Real secrets: remove immediately, replace with env var reference, add to .gitignore
  • NEVER commit real API keys, tokens, or credentials

Step 6 — Middleware auth check (JS/TS projects)

Verify all non-public routes have auth middleware:

grep -rn "router\.\(get\|post\|put\|delete\)" api/src/routes/ 2>/dev/null \
  | grep -v "requireAuth\|public\|health\|webhook" | head -20 || true

Report any routes missing auth middleware.


Step 7 — Report remaining unfixable issues

For each vulnerability that cannot be fixed:

  • Transitive deps: name the direct dependency pulling it in
  • Install-time only: mark as "install-time only, not a runtime risk"
  • Major version required to fix: note the breaking change risk
  • Exception matched: reference the exception that allows it

Gate verdict

=== Security Gate Verdict ===
Frontend vulns: Critical X | High X | Moderate X | Low X
Backend vulns:  Critical X | High X | Moderate X | Low X
Python vulns:   Critical X | High X | Moderate X | Low X
Fixed:          N vulnerabilities
Known exceptions accepted: [list]
Remaining blocking:        [list — must fix before commit]
Secrets:        None found ✅ | [findings]
Auth middleware: ✅ all routes protected | [unprotected routes]
Status:         PASSED ✅ | BLOCKED ❌ (critical/high remain or real secrets found)

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。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

Act as a Senior Accessibility Engineer to audit a page, component, or design against WCAG 2.2 AA. Produces a triaged finding list (critical/serious/moderate), focus-order map, contrast report, ARIA decision tree, and a screen-reader test plan. Use when shipping new UI, hardening an existing flow, or preparing for VPAT/accessibility conformance.

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。

rajitsaha/100xprism102026年10月14日 更新

When the user wants to plan, design, or implement an A/B test or experiment — "split test," "variant copy," "multivariate test," "hypothesis," "statistical significance," "how long should I run this test," or comparing two versions. For tracking implementation, see analytics-tracking. For page-level conversion optimization, see page-cro.

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。

rajitsaha/100xprism102026年10月14日 更新

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, full variations — for any paid platform; 'ad copy variations,' 'RSA headlines,' 'bulk ad copy,' 'creative testing,' 'write me some ads.' For campaign strategy and targeting, see paid-ads. For landing page copy, see copywriting.

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。

rajitsaha/100xprism102026年10月14日 更新

ai-seo

無料

When the user wants content cited by LLMs or surfaced in AI-generated answers — 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'AI Overviews,' 'optimize for ChatGPT/Perplexity/Claude,' 'AI citations,' 'zero-click search.' For traditional technical/on-page audits, see seo-audit. For structured data, see schema-markup.

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。

rajitsaha/100xprism102026年10月14日 更新

When the user wants to set up, improve, or audit analytics tracking and measurement — "GA4," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "tracking plan," "attribution," "Mixpanel," "Segment," "are my events firing," or how to measure marketing results. For A/B test measurement, see ab-test-setup.

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。

rajitsaha/100xprism102026年10月14日 更新

architect

無料

Architectural decision advisor for cloud, data, and SaaS distributed systems. Use when the user asks "should we use X or Y", weighs a tradeoff, or needs a decision matrix, scaling analysis, cost-at-scale review, data-tier design, multi-tenancy model, or API/resilience guidance. For full technical blueprints, use enterprise-design.

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。

rajitsaha/100xprism102026年10月14日 更新

rajitsaha のスキルをすべて見る

このスキルの問題を報告する