ClawAudit verdict
lead-guardian
Real-estate lead response skill using Twilio SMS and OpenRouter AI; all integrations are transparently documented with user-supplied credentials for the stated purpose of lead qualification.
⚠ 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 (4)
Possible hardcoded credential
SKILL.md · code · TOKEN="your_token
<script> tag in markdown — potential code injection
app.py · prose · downgraded · <script>
Python os.getenv — reads environment variable
app.py · prose · downgraded · os.getenv(
POSTs data to external URL
app.py · prose · downgraded · .post(
'https://
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.