product-master
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a prompt generation engine, using local templates and a database of photography terms to build complex strings for image generation. The logic is strictly focused on text manipulation.
- [COMMAND_EXECUTION]: Python code within
modules/core/builder.mdinteracts with a local database file atextracted_results/elements.db. The code implements search and assembly logic that is safe and limited to string formatting for output. - [PROMPT_INJECTION]: While the skill uses strong instructional language such as 'CRITICAL
- HIGHEST PRIORITY' in
modules/layouts/grid_collage.md, these instructions are intended to ensure consistency in the resulting Midjourney image prompts and do not target the agent's core safety or operational constraints.
Audit Metadata