パッケージ
agentworks/secure-skills
Curated, low-risk skills for code review, research, and triage.
Trust means
Trust score is a heuristic blend of popularity, freshness, structure quality, and safety penalties. Useful for ranking, not a guarantee.
Risk means
Risk is generated by automated scans of skills, files, and allowed tools. It is not the same thing as a human security review.
Review status
Auto-scanned only. No major risk signals were detected, but that still does not mean manually reviewed or guaranteed safe.
リスク: 低（allowed-tools limited to read/grep/glob）
スター
1,280
フォーク
120
スキル
2
ファイル
3
Suitable for
Teams that care about trust posture, explainability, and controlled adoption before they let a workflow package into normal use.
Not suitable for
Not enough on its own for high-assurance environments that require formal review, threat modeling, or vendor approval.
Install prerequisites
What to verify before touching install
- Treat this page as triage, not as a finished security assessment.
- Review the repo and the highest-risk skills yourself before installation.
- Decide what extra internal approval is required for your environment.
- Tooling check: this package references Read, Grep, Glob as part of its skills.
Recommended first read
fast-triage
Prioritize issues with quick risk scoring.
パス: skills/fast-triage
Allowed tools: Read, Grep
Risk level: 低
After install
How to verify it actually works
Core skills
What this package actually helps you do
許可ツール: Read, Grep
許可ツール: Read, Grep, Glob
Package contents
Folders and files
fast-triage
skills/fast-triage
Prioritize issues with quick risk scoring.
- SKILL.md.md
secure-review
skills/secure-review
Review code changes for security regressions.
- SKILL.md.md
- checklist.md.md
Last step
Install only after the checks above
If the package fits your workflow, the starter skill makes sense, and the auto-scan signals are acceptable for your environment, then use the exact install command below.
Install command
npx skills add agentworks/secure-skills
Claude Code
Copy to .claude/skills/
GitHub Copilot
Copy to .github/skills/
Codex CLI
Copy to .agents/skills/
Gemini CLI
Copy to .gemini/skills/
Community Signals
What users think
関連パッケージ
Similar packages worth comparing
mukul975/Anthropic-Cybersecurity-Skills
753+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Works with Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI & 20+ platforms · Penetration testing, DFIR, threat intel, cloud security & more · Apache 2.0
alinaqi/claude-bootstrap
Opinionated project initialization for Claude Code. Security-first, spec-driven, AI-native.
k-kolomeitsev/data-structure-protocol
Graph-based long-term memory skill for AI (LLM) coding agents — faster context, fewer tokens, safer refactors
wrsmith108/varlock-claude-skill
Claude Code skill for secure environment variable management with Varlock. Never expose secrets in Claude sessions.