design-with-images
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, network exfiltration commands, or sensitive file access. It is an instructional markdown file guiding a visual design process.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests external data in the form of image-generation outputs and user-selected concepts.
- Ingestion points: External image generation skill outputs and user-provided design selections.
- Boundary markers: No explicit markers are defined to delineate external design instructions from the agent's core instructions.
- Capability inventory: The skill guides the agent to implement design code and utilize local auxiliary tools for screenshot comparison (
compare-screenshots) and review (screenshot-critique). - Sanitization: No specific sanitization or validation of the design reference data is described.
Audit Metadata