ClawAudit verdict
undo
The skill provides a file edit time machine for AI agents, which may pose a risk if not properly validated.
⚠ 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 (5)
apt-get install — installs system packages
SKILL.md · prose · downgraded · apt-get install
References child_process — can spawn system processes
lib/git.js · prose · downgraded · child_process
yum install — installs system packages
scripts/init.js · prose · downgraded · yum install
apk add — installs Alpine packages
scripts/init.js · prose · downgraded · apk add
References sudo — requests elevated privileges
scripts/init.js · prose · downgraded · sudo
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.
Is this flag fair?
Thanks — recorded.