canvas-design
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security issues were identified in the skill instructions or supplementary files. The skill operates by providing artistic principles and steering the AI toward high-quality visual generation.
- [NO_CODE]: The skill consists entirely of markdown instructions and text-based font license agreements. There are no executable scripts (Python, JavaScript, shell), binaries, or configuration files that could trigger command execution.
- [EXTERNAL_DOWNLOADS]: The instructions suggest downloading and using fonts to enhance visual designs. The provided license files contain references to well-known and trusted source repositories, such as the Google Fonts GitHub organization and the Vercel Geist project, which are considered safe sources.
- [PROMPT_INJECTION]: The skill uses assertive language and pre-filled conversation context (e.g., instructing the agent to act as if a user requested a 'masterpiece') to improve output quality. These are evaluated as benign prompt engineering strategies common in creative assistant skills rather than attempts to bypass safety filters or extract sensitive data.
Audit Metadata