ClawAudit verdict
docker-helper
The skill's content outlines a Docker helper process with no malicious intent.
⚠ 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)
Accesses sensitive system files
scripts/docker.sh · prose · downgraded · /etc/hosts
Recursive delete from root or home — destructive command
scripts/docker.sh · prose · downgraded · rm -rf /
apt-get install — installs system packages
scripts/docker.sh · prose · downgraded · apt-get install
Changes file ownership
scripts/docker.sh · prose · downgraded · chown
Python urllib.request — network access
scripts/docker.sh · prose · downgraded · urllib.request
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C). 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.