Caveat verdict

hudl-model-switch

88
๐ŸŸข Trusted
No high-risk patterns surfaced by the deep scan โ€” automated capability review, not behavioral proof.

A model-switching utility for the Huddle01 GRU gateway that edits local OpenClaw config via a script; executionSinkDetected is from the documented shell script invocation, consistent with the stated config management purpose.

โš  Flagged for review โ€” coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis โ€” not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

40
security
90
transparency
70
maintenance

Findings (3)

Pattern match critical

Recursive delete from root or home โ€” destructive command

README.md ยท code ยท rm -rf ~

Pattern match high

Accesses OpenClaw config/secrets directly

README.md ยท code ยท ~/.openclaw/openclaw.json

Pattern match medium

References sudo โ€” requests elevated privileges

scripts/switch-model.sh ยท prose ยท downgraded ยท sudo

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/F). Final tier capped at Caution โ€” cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API