ClawAudit verdict
agent-workflow
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
Manages a persistent state machine for task planning and execution without external data exfiltration.
⚠ 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.
80
security
100
transparency
80
maintenance
Findings (2)
Pattern match medium
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Pattern match medium
Dynamic import() — loads module at runtime
dist/index.d.ts · prose · downgraded · import("
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.