canvas-design

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided concepts and instructions as the foundation for creating visual art.
  • Ingestion points: The skill takes user input in the 'DESIGN PHILOSOPHY CREATION' step within SKILL.md.
  • Boundary markers: No specific delimiters or warnings to ignore instructions within the user input are provided.
  • Capability inventory: The skill is capable of generating markdown, PDF, and PNG files.
  • Sanitization: There are no instructions to sanitize or validate the user input before processing.
  • [EXTERNAL_DOWNLOADS]: In SKILL.md, the instruction 'Download and use whatever fonts are needed to make this a reality' directs the agent to fetch external resources from unrestricted and unspecified remote sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 06:09 AM