ClawAudit verdict
embodied-ai-weekly
Automated weekly report generator that fetches public data from arXiv and GitHub APIs; all network calls are to public read-only endpoints with no credential access or sensitive data transmission.
⚠ 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 (2)
<script> tag in markdown — potential code injection
references/html_template_guide.md · code · <script>
Popular HTTP library — network access
SKILL.md · code · axios
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.