Agent skill
agent-shield
Run ecc-agentshield security scan against Claude Code configuration
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/agent-shield-itsmattg-property-tracker
SKILL.md
AgentShield Security Scan
Scans .claude/ configuration for security vulnerabilities using ecc-agentshield.
When to Run
- After modifying hooks, skills, or CLAUDE.md
- After adding MCP servers or updating mcp.json
- Before merging infrastructure PRs
- Periodically as part of security hygiene
Quick Scan (Static Analysis)
Run 102 static rules against hooks, skills, CLAUDE.md, settings.json:
npx ecc-agentshield scan --path .claude/ --format markdown
Save results:
npx ecc-agentshield scan --path .claude/ --format markdown > .claude/phases/output/security-scan-$(date +%Y-%m-%d).md
Deep Scan (3-Agent Opus Pipeline)
Requires ANTHROPIC_API_KEY env var. Runs red-team, blue-team, and auditor agents:
npx ecc-agentshield scan --path .claude/ --opus --stream
What It Checks
| Category | Examples |
|---|---|
| Secrets | Hardcoded API keys in CLAUDE.md, env vars in hooks |
| Permissions | Overly broad Bash(*) allows, missing deny lists |
| Injection | Shell variable interpolation in Python heredocs, unquoted vars |
| MCP | Risky servers, npx -y auto-install, hardcoded secrets |
| Hooks | Data exfiltration, silent error suppression, command injection |
Interpreting Results
Grades: A (90-100) through F (0-39). Focus on HIGH and CRITICAL findings first. MEDIUM findings are good improvement opportunities. LOW can be addressed opportunistically.
After Scanning
- Fix all CRITICAL/HIGH findings immediately
- Create tasks for MEDIUM findings
- Document any accepted risks in CLAUDE.md
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?