ClawAudit verdict
openclaw-autoupdate
Performs a global npm package installation (npm install -g openclaw) which could install arbitrary code from the npm registry; the skill itself acknowledges this triggers security scanner warnings, and the SHA256 hash claim cannot be verified from the SKILL.md alone.
⚠ 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 (1)
Recursive delete from root or home — destructive command
scripts/silent-update.sh · prose · downgraded · rm -rf /
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.