canvas-design

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a collection of instructions for creating visual art and design philosophies. It does not contain any executable code, network exfiltration patterns, or credential harvesting attempts.
  • [EXTERNAL_DOWNLOADS]: The instructions suggest the agent 'Download and use whatever fonts are needed to make this a reality.' This indicates a potential for external network access to fetch font assets, which is a functional requirement for its stated purpose and not inherently malicious.
  • [PROMPT_INJECTION]: The skill uses simulated user feedback ('The user ALREADY said "It isn't perfect enough..."') to reinforce a high-quality, 'masterpiece' persona. This is a steering technique for persona consistency rather than a malicious bypass or safety override.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 02:33 AM
Security Audit — agent-trust-hub — canvas-design