Caveat verdict
writing-tone-clone
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Analyzes writing samples to extract voice patterns and generates a deployable voice skill file; operates purely on user-provided text with no network or credential access.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
70
security
100
transparency
90
maintenance
Findings (1)
Pattern match critical
Writes to SKILL.md — self-modifying skill
SKILL.md · frontmatter · SKILL.md that replicates that person's exact writing style. Triggers on "write
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.