image-to-code
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and interpret external visual data (mockups, screenshots) to generate functional interface code, creating a surface for instructions embedded in data to influence agent behavior.
- Ingestion points: User-provided images and screenshots, as well as images generated via external tools like
imagegen-web(SKILL.md). - Boundary markers: The instructions do not define boundary markers or explicit commands to ignore instructions found within the visual content of the images.
- Capability inventory: The skill's primary function involves generating UI code (JSX, markup), which requires file-writing capabilities to persist the output.
- Sanitization: There is no evidence of sanitization or filtering of text extracted from images before it is used to generate code.
Audit Metadata