ClawAudit verdict
text-preserve
nano-banana-korean-rendering
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
The skill focuses on rendering text accurately in AI images, using Canvas and Gemini, without apparent security risks.
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.
100
security
90
transparency
80
maintenance
No red flags detected in static analysis.
Checked: 115 threat patterns · AST capability extraction · cross-zone compound shapes · permission integrity.
Permissions & capabilities
No declared permissions — minimal attack surface.
data_encoding Was this verdict right?
Thanks — recorded.