ClawAudit verdict
bootcamp
The skill runs a local bash script to discover OpenClaw CLI commands and generates a reference document saved locally; executionSinkDetected reflects local bash execution with no 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.
Findings (4)
Possible hardcoded credential
bootcamp.sh · prose · downgraded · token="${token%,}
Pipe-to-python pattern — remote code execution risk
bootcamp.sh · prose · downgraded · curl -sL --connect-timeout 5 --max-time 15 "$url" 2>/dev/null | python
Pipe to python — executes piped content as Python code
bootcamp.sh · prose · downgraded · | python3
Accesses OpenClaw config/secrets directly
bootcamp.sh · prose · downgraded · ~/.openclaw/openclaw.json
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/C/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.