canvas-design

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill employs strong directives and simulated user feedback (e.g., 'The user ALREADY said "It isn't perfect enough..."') to shape the agent's behavior and enforce an expert persona. These techniques are used here as stylistic constraints for the primary task of visual design rather than for bypassing safety guidelines.
  • [SAFE]: The skill incorporates a large collection of SIL Open Font License files in the canvas-fonts directory. These are standard legal documents for third-party font assets and contain no executable code or malicious instructions.
  • [SAFE]: No network exfiltration, hardcoded credentials, or dangerous command execution patterns were detected across the skill files. The instructions focus entirely on the generation of markdown, PDF, and PNG artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 08:13 PM