canvas-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to use user-provided input as the foundation for creating design philosophies and visual art, which can be exploited to influence agent behavior through embedded instructions.
- Ingestion points: User input and 'subtle conceptual threads' are ingested in SKILL.md.
- Boundary markers: No delimiters or instructions to ignore embedded commands are present.
- Capability inventory: The skill creates and writes files (.md, .pdf, .png) and utilizes font rendering tools.
- Sanitization: No sanitization or validation of the input is performed before processing.
- [EXTERNAL_DOWNLOADS]: The skill instructions explicitly direct the agent to 'Download and use whatever fonts are needed,' which results in the agent accessing external network resources to fetch data files. This creates a risk if the agent retrieves resources from untrusted or malicious sources.
Audit Metadata