ClawAudit verdict
openclaw-config-safety
The skill validates and normalizes OpenClaw configuration changes safely.
⚠ 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.
Permission integrity
file_read
Findings (4)
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/openclaw.json
Possible hardcoded credential
test/export.test.js · prose · downgraded · apiKey: "${MINIMAX_API_KEY}
References child_process — can spawn system processes
src/doctor-check.js · prose · downgraded · child_process
Accesses sensitive environment variables
test/import.test.js · prose · downgraded · process.env.TEST_API_KEY
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). 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.
data_encodingfile_read Is this flag fair?
Thanks — recorded.