ClawAudit verdict
llm-memory-integration
llm-memory-v8-fix
The skill automatically clones an opaque private package from cnb.cool into a 'privileged' directory on every install and startup, executing arbitrary remote code whose contents are unknown; while the behavior is disclosed, installing and running unauditable private code from a third-party host into a privileged path is a genuine supply-chain risk.
⚠ 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 (3)
subprocess execution — runs system commands from Python
hooks/onStartup.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
hooks/onStartup.py · prose · downgraded · os.environ.get(
Python shutil file operation — copies/moves/deletes files
hooks/postinstall.py · prose · downgraded · shutil.rmtree(
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
Requires 3 system binaries. (1 elevated: git).
Is this flag fair?
Thanks — recorded.