ClawAudit verdict
coding-pipeline
Describes a disciplined coding process; contains no commands that could be malicious.
⚠ 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.
Findings (4)
Pipe to python — executes piped content as Python code
assets/PHASE-3-validator-checklist.md · prose · downgraded · | Python
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · quietly
References agent configuration files
references/integration.md · code · CLAUDE.md
References agent memory files
references/openclaw-integration.md · code · MEMORY.md
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.