canvas-design
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional, defining a two-step process for generating creative designs and manifestos. It does not contain any executable scripts or binary files.
- [SAFE]: The skill includes license documentation for numerous well-known fonts (e.g., Google Fonts, Vercel, IBM). These resources are from trusted organizations and are used appropriately for the skill's primary purpose of visual design.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user input to derive conceptual themes for its creative outputs, creating a standard ingestion surface.
- Ingestion points: User input serves as the foundation for the 'Design Philosophy Creation' step in
SKILL.md. - Boundary markers: The skill does not provide specific markers or instructions to delimit user-provided content from agent instructions.
- Capability inventory: The skill allows the agent to generate .md, .png, and .pdf files.
- Sanitization: There is no evidence of specific sanitization or filtering logic applied to user input before it is used to generate manifestos and artwork.
Audit Metadata