ClawAudit verdict

subagent-architecture

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill is used for advanced subagent orchestration and appears to be transparent in its capabilities and usage.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

38
security
80
transparency
90
maintenance

Findings (5)

Pattern match high

Possible hardcoded credential

examples/security-proxy-usage.js · prose · downgraded · api_key: 'sk-abc123def456

Pattern match high

Accesses sensitive system files

lib/spawn-security-proxy.js · prose · downgraded · /etc/passwd

Pattern match medium

Uses spawn() — can execute external programs

SKILL.md · prose · downgraded · spawn (

Pattern match medium

References agent memory files

templates/security-proxy.md · code · MEMORY.md

Pattern match low

Popular HTTP library — network access

lib/spawn-security-proxy.js · prose · downgraded · got

Permissions & capabilities

No declared permissions — minimal attack surface.

process_execcredential_access

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API