canvas-design

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The instructions in SKILL.md direct the agent to "Download and use whatever fonts are needed to make this a reality." This encourages the fetching of external font files from unspecified remote sources during execution, which may lead to the ingestion of unverified assets.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided conceptual input to establish the aesthetic language and conceptual DNA of the generated artwork.
  • Ingestion points: User instructions used as a foundation for "Design Philosophy Creation" and establishing a "Subtle Reference."
  • Boundary markers: None; the skill encourages taking user input into account as a foundation for creative freedom without explicit delimiters or safety instructions regarding the content of that input.
  • Capability inventory: The skill allows creating, writing, and downloading files in .md, .pdf, and .png formats.
  • Sanitization: None; user-supplied concepts are directly interpreted and expressed through the agent's visual design outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 07:23 AM