ClawAudit verdict
huo15-plan-mode
Dangerous operation confirmation mechanism that pauses and requires user confirmation before executing risky commands; the skill purpose is to ADD a safety gate not remove one.
⚠ 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
package_install
Findings (2)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
Accesses shell history/config
scripts/plan-mode.sh · prose · downgraded · ~/.zshrc
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.
package_install Is this flag fair?
Thanks — recorded.