メニュー
Detect hardcoded credentials, API keys, tokens, and secrets in source code and configuration files. Use when reviewing code for leaked secrets before commit/merge, auditing a repository for credential exposure, or setting up secret detection.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Security-focused review of native Android and iOS mobile app source code against OWASP MASVS v2.1.0. Use when reviewing mobile codebases, mobile PR diffs, or auditing a mobile module.
Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and missing guardrails. Use when reviewing CLAUDE.md files, MCP configs, agent orchestration code, or any AI agent setup.
Assess agentic AI applications against the OWASP Top 10 for Agentic Applications 2026. Use when reviewing autonomous AI agents, multi-agent systems, or agentic workflows for security risks including goal hijacking, tool misuse, privilege abuse, and rogue agent behavior.
Comprehensive LLM security assessment against OWASP Top 10 for LLM Applications 2025. Use when reviewing LLM-integrated applications, RAG pipelines, chatbots, AI agents, or GenAI features. Covers prompt injection, data poisoning, supply chain, excessive agency, and more with real-world attack scenarios and testing methodologies.
Security review of MCP (Model Context Protocol) server implementations and configurations. Use when auditing MCP server source code, evaluating third-party MCP servers before installation, or reviewing Claude Code MCP integrations for overpermissioning, injection risks, and data exposure.
Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy. Use when red-teaming AI apps, validating guardrails, or deepening LLM01 (Prompt Injection) assessments.
| name | secrets-scan |
| description | Detect hardcoded credentials, API keys, tokens, and secrets in source code and configuration files. Use when reviewing code for leaked secrets before commit/merge, auditing a repository for credential exposure, or setting up secret detection. |
| license | CC-BY-4.0 |
Detect hardcoded secrets by following the full procedure in plays/secrets-scan.md.
Run Automated Scanner — Use available tools in preference order:
trufflehog filesystem --directory=<path> --json (recommended)trufflehog git file://<repo> --json (includes git history)gitleaks detect --source=<path> --report-format=jsondetect-secrets scan <path> --all-filesManual Pattern Analysis — Search for high-confidence patterns:
AKIA...), OpenAI (sk-...), Anthropic (sk-ant-...), GitHub (ghp_...), Slack (xoxb-...), Stripe (sk_live_...), SendGrid (SG.)://user:pass@host).env, docker-compose*.yml, *.tfvars, terraform.tfstate, kubeconfig, .npmrc, .pypircContextual Analysis — For each detection: Is it real (not a placeholder/test fixture)? Is it active? What's the blast radius (service, permissions, prod vs dev, exposure duration)?
Check Preventive Controls — Verify: .gitignore covers sensitive files, pre-commit hooks for secret scanning, CI pipeline scanning, secrets management documentation.
Important: Never include actual secret values in findings. Show redacted versions only (e.g., AKIA****EXAMPLE). Active production secrets require immediate rotation.
Scan summary, findings using templates/finding.md, preventive controls checklist, and immediate rotation actions if needed.