メニュー
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
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
The Evaluate-Loop coordinator for soe. Runs the BRAINSTORM → PLAN → EVALUATE_PLAN → EXECUTE → EVALUATE_EXEC → (FIX↺ | COMPLETE) state machine for a track: dispatches leaf agents, dispatches workers into isolated worktrees and applies their validated returns serially, and is the SOLE writer of .soe/tracks/{id}/state.json. Resumes crash-safely from committed state and bounds its fix/plan loops. Use when: 'run the loop', 'orchestrate', 'run the track', 'evaluate-loop', 'drive the track to completion'.
Session-model-led multi-model tiering. Use in ANY conversation (ambient) or in the pipeline to decide which model tier does which slice of work, and to delegate to the right model-pinned agent (strategist/deep-reasoner/fast-worker). The session model you selected IS the orchestrator; it self-selects its topology from its own model identity.
Use when the orchestrator needs to delegate an implementation task to an isolated worker — dispatches each worker as a Task-tool subagent in its own git worktree, awaits its return as the completion signal, and applies results serially as the sole state.json writer behind a validated context firewall
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use at run start to discover what reviewers/analyzers/generators any installed plugin provides and route work by ROLE. Builds a role→provider map via lib/capability-scan.js so the loop prefers the best-matching installed specialist (a Go reviewer, a Flutter reviewer, AgentShield, ...) and falls back to soe-core's generic (soe:code-reviewer, soe:security-reviewer, soe:architect, ...) when none is installed. soe-core is self-sufficient and NEVER hard-depends on packs.
| name | security-scan |
| description | Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions. |
| metadata | {"adopted-into":"soe","origin":"ECC (Everything Claude Code) — security-scan"} |
Audit your Claude Code configuration for security issues using AgentShield.
In soe: this skill backs the build/release-time engine self-audit (
/soe:self-audit) — soe reviewing its OWN plugin config (the "airframe"), distinct from the runtime adversarial gate. AgentShield runs locally via theecc-agentshieldnpm package against the.claude// plugin config; the core local scan is free (MIT) with no Pro/hosted dependency. The only optional cloud path is the--opusdeep-analysis pipeline, which needs your ownANTHROPIC_API_KEYand is never required for a scan.
.claude/settings.json, CLAUDE.md, or MCP configs| File | Checks |
|---|---|
CLAUDE.md | Hardcoded secrets, auto-run instructions, prompt injection patterns |
settings.json | Overly permissive allow lists, missing deny lists, dangerous bypass flags |
mcp.json | Risky MCP servers, hardcoded env secrets, npx supply chain risks |
hooks/ | Command injection via interpolation, data exfiltration, silent error suppression |
agents/*.md | Unrestricted tool access, prompt injection surface, missing model specs |
AgentShield must be installed. Check and install if needed:
# Check if installed
npx ecc-agentshield --version
# Install globally (recommended)
npm install -g ecc-agentshield
# Or run directly via npx (no install needed)
npx ecc-agentshield scan .
Run against the current project's .claude/ directory:
# Scan current project
npx ecc-agentshield scan
# Scan a specific path
npx ecc-agentshield scan --path /path/to/.claude
# Scan with minimum severity filter
npx ecc-agentshield scan --min-severity medium
# Terminal output (default) — colored report with grade
npx ecc-agentshield scan
# JSON — for CI/CD integration
npx ecc-agentshield scan --format json
# Markdown — for documentation
npx ecc-agentshield scan --format markdown
# HTML — self-contained dark-theme report
npx ecc-agentshield scan --format html > security-report.html
Apply safe fixes automatically (only fixes marked as auto-fixable):
npx ecc-agentshield scan --fix
This will:
Run the adversarial three-agent pipeline for deeper analysis:
# Requires ANTHROPIC_API_KEY
export ANTHROPIC_API_KEY=your-key
npx ecc-agentshield scan --opus --stream
This runs:
Scaffold a new secure .claude/ configuration from scratch:
npx ecc-agentshield init
Creates:
settings.json with scoped permissions and deny listCLAUDE.md with security best practicesmcp.json placeholderAdd to your CI pipeline:
- uses: affaan-m/agentshield@v1
with:
path: '.'
min-severity: 'medium'
fail-on-findings: true
| Grade | Score | Meaning |
|---|---|---|
| A | 90-100 | Secure configuration |
| B | 75-89 | Minor issues |
| C | 60-74 | Needs attention |
| D | 40-59 | Significant risks |
| F | 0-39 | Critical vulnerabilities |
Bash(*) in the allow list (unrestricted shell access)${file} interpolation2>/dev/null, || true)npx -y auto-install in MCP server configs