imagegen-frontend-web
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains no executable code, remote script downloads, or sensitive file access patterns. It consists entirely of art direction instructions for an image generation model.
- [PROMPT_INJECTION]: The skill uses directive language (e.g., 'CRITICAL OUTPUT RULE', 'HARD OUTPUT RULE') to enforce stylistic and formatting constraints, such as the number of images generated per section. These are benign functional instructions and do not target agent safety filters.
- [PROMPT_INJECTION]: The skill operates on user-provided descriptions to guide image generation, which is the primary intended purpose. 1. Ingestion points: User-provided briefs for website designs. 2. Boundary markers: Absent. 3. Capability inventory: Image generation tool invocation. 4. Sanitization: Absent. This surface is evaluated as safe given its functional nature and limited impact context.
Audit Metadata