canvas-design
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides detailed instructions for aesthetic tasks such as creating design philosophies and visual artwork. No harmful command execution, network exfiltration, or safety bypass mechanisms were detected.\n- [PROMPT_INJECTION]: The skill accepts user-supplied conceptual input to inform artistic creation, which represents a surface for indirect prompt injection. However, the risk is minimal as the skill's primary function is restricted to producing document-based art objects.\n
- Ingestion points: Subtle niche references and instructions provided by the user (SKILL.md).\n
- Boundary markers: Absent.\n
- Capability inventory: File generation and writing for .md, .pdf, and .png formats (SKILL.md).\n
- Sanitization: Absent.
Audit Metadata