ClawAudit verdict
legaldoc-ai
Legal document automation skill for contract analysis, clause extraction, and deadline tracking using a legaldoc CLI; network_in/credential capabilities appear for API-based legal research, all serving the documented legal professional workflow.
⚠ 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
credential_access
Findings (5)
Possible hardcoded credential
SKILL.md · code · api_key: "${CLIO_API_KEY}
subprocess execution — runs system commands from Python
execution/legaldoc.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
execution/deadline_tracker.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
execution/legal_research.py · prose · downgraded · urllib.request
References webhook/callback URL
templates/config.yaml · prose · downgraded · webhook_url
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.
network_incredential_access Is this flag fair?
Thanks — recorded.