canvas-design
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill employs behavioral steering by pre-defining user feedback ("The user ALREADY said...") to prioritize high-quality artistic output. This instruction-override pattern is used for creative alignment and does not attempt to bypass safety constraints.- [EXTERNAL_DOWNLOADS]: The instructions permit the agent to fetch additional fonts if necessary for the design task. This refers to standard design assets used to fulfill the skill's primary function of visual creation and is considered safe within this context.
Audit Metadata