ClawAudit verdict
project-factory
Multi-phase project scaffolding skill that uses LLM reasoning internally with no external API calls in Phase 0; execution sinks are documented project setup workflows (docker, cargo, curl to localhost) with no exfiltration or malicious patterns.
⚠ 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 (5)
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | python3
Accesses OpenClaw config/secrets directly
scripts/bootstrap_project.py · prose · downgraded · ~/.openclaw/openclaw.json
subprocess execution — runs system commands from Python
scripts/allprojects_check.py · prose · downgraded · subprocess.run(
Instructs covert action — may act without user awareness
scripts/bootstrap_project.py · prose · downgraded · silently
References agent memory files
references/onboarding_checklist.md · prose · downgraded · MEMORY.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.