tweaks
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features an ingestion point where it processes user-supplied HTML artifacts (SKILL.md). There are no explicit boundary markers or sanitization processes mentioned for this external data. The resulting artifacts have the capability to perform 'localStorage' operations and 'postMessage' communication with the host environment. This represents an indirect prompt injection surface, although it is consistent with the skill's primary function.
- [SAFE]: The use of 'localStorage' to persist UI settings like accent colors and theme modes is a standard, safe web practice.
- [SAFE]: External resource links are restricted to well-known services, specifically Google Fonts for typography.
Audit Metadata