canvas-design
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill utilizes a context manipulation technique in
SKILL.mdby fabricating a previous user turn ('The user ALREADY said...') to override the interaction state and force a specific reasoning mindset. - [PROMPT_INJECTION]: The instructions employ aggressive persona-steering and authoritative language to manipulate the agent's self-perception and operational constraints.
- [EXTERNAL_DOWNLOADS]: The
canvas-fontsdirectory contains license files with links to external font repositories. These references target official project domains and well-known service providers.
Audit Metadata