ClawAudit verdict
yuyonghao-observability
The skill collects and monitors system data, which may potentially expose sensitive data.
⚠ 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
file_read
package_install
Findings (4)
<script> tag in markdown — potential code injection
src/dashboard.js · prose · downgraded · <script>
References webhook/callback URL
src/alert-manager.js · prose · downgraded · webhookUrl
Popular HTTP library — network access
src/alert-manager.js · prose · downgraded · node-fetch
Node http/https module — low-level network access
src/dashboard.js · prose · downgraded · require('http')
Permissions & capabilities
No declared permissions — minimal attack surface.
package_installfile_readnetwork_in Is this flag fair?
Thanks — recorded.