ClawAudit verdict
china-summarizer
Content summarization skill that uses the host LLM built-in capabilities plus browser/file access to read content — no external API keys required and no data sent to third parties beyond the host platform.
⚠ 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 (2)
<script> tag in markdown — potential code injection
SKILL.md · code · <script>
References sudo — requests elevated privileges
SKILL.md · code · sudo
Permissions & capabilities
Requires 1 system binary.
package_install Is this flag fair?
Thanks — recorded.