ugc-mobile
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill constructs prompts for an AI video generation service by filling template placeholders with user-provided information. \n
- Ingestion points: User input is accepted for multiple placeholders such as
[APP NAME],[RESULT], and[FEATURE]inSKILL.md. \n - Boundary markers: The templates do not utilize boundary markers or explicit instructions to ignore instructions embedded within user-supplied text. \n
- Capability inventory: The generated prompts are intended to be processed by a video generation tool via the
POST /videos/generateAPI endpoint. \n - Sanitization: There is no evidence of input validation or sanitization applied to the user-provided values before interpolation into the final generated prompt.
Audit Metadata