ClawAudit verdict
prose-to-deck
The skill transforms long-form writing into polished single-file HTML presentations. It does not contain any malicious code or intent.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ 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 โ potential code injection
references/materials.md ยท prose ยท downgraded ยท <script>
Instructs covert action โ may act without user awareness
SKILL.md ยท prose ยท downgraded ยท silently
Permissions & capabilities
No declared permissions โ minimal attack surface.
Is this flag fair?
Thanks โ recorded.