book-cover-design
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows established practices for AI-assisted design and correctly identifies that AI-generated text is unreliable, advising the use of external design tools.
- [EXTERNAL_DOWNLOADS]: Fetches installation guidelines and supplemental skills from the official inference-sh GitHub organization. This is a legitimate dependency for the skill's core functionality.
- [COMMAND_EXECUTION]: Executes remote image generation models via the belt CLI. All commands are well-documented and consistent with the skill's stated purpose of book cover creation.
- [PROMPT_INJECTION]: Contains an indirect injection surface where user-defined text is interpolated into JSON payloads for image generation models in SKILL.md. Boundary markers are absent, and no sanitization is applied to these prompt strings, which is standard for image generation workflows.
Audit Metadata