ClawAudit verdict
openclaw-team-builder
The skill appears to manage OpenClaw agent teams and perform various operations, with no apparent malicious intent.
⚠ 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
scripts/team-builder.sh · prose · downgraded · | python3
Possible hardcoded credential
scripts/team-builder.sh · prose · downgraded · secret="${B_FEISHU_SECRET:-}
Accesses OpenClaw config/secrets directly
scripts/team-builder.sh · prose · downgraded · ~/.openclaw/openclaw.json
Python os.environ.get — reads environment variable
scripts/team-builder.sh · prose · downgraded · os.environ.get(
Permissions & capabilities
Requires 2 system binaries.
Is this flag fair?
Thanks — recorded.