canvas-design
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill uses simulated conversation history to influence the agent's behavior. In the 'FINAL STEP' section of 'SKILL.md', the instructions state: 'The user ALREADY said "It isn't perfect enough. It must be pristine..."'. This technique injects a fake user state to force the agent into a refinement loop.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied "subtle references" or instructions as a conceptual foundation for generating artwork. This creates an attack surface where malicious instructions could be embedded in the user's conceptual input.
- Ingestion points: User-provided conceptual threads and subtle references in 'SKILL.md'.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the user input.
- Capability inventory: The skill is capable of generating and saving markdown, PDF, and PNG files.
- Sanitization: No evidence of input sanitization or validation of the conceptual threads was found.
- [EXTERNAL_DOWNLOADS]: The instructions in 'SKILL.md' explicitly tell the agent to "Download and use whatever fonts are needed to make this a reality." This encourages the agent to fetch external assets from the internet without specifying trusted sources or providing integrity validation mechanisms.
Audit Metadata