security-scan
AgentShield を使用して、Claude Code の設定（.claude/ ディレクトリ）のセキュリティ脆弱性、設定ミス、インジェクションリスクをスキャンします。CLAUDE.md、settings.json、MCP サーバー、フック、エージェント定義をチェックします。
82
73%
Does it follow best practices?
Impact
97%
2.25xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/ja-JP/skills/security-scan/SKILL.mdSecurity
1 medium severity finding. This skill can be installed but you should review these findings before use.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.80). This skill explicitly requires installing/running the ecc-agentshield package (npx ecc-agentshield / npm package https://www.npmjs.com/package/ecc-agentshield and its repo https://github.com/affaan-m/agentshield), which fetches and executes remote code at runtime and (per the Opus 3‑agent pipeline described) launches agents that generate and control prompts, so the external URLs are runtime dependencies that can control prompts/execute code.
- Repository
- affaan-m/everything-claude-code
- Commit
5df943e
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.