skills/plurigrid/asi/canvas-design/Gen Agent Trust Hub

canvas-design

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill utilizes the Python libraries 'Pillow' and 'cairo' for image generation. As the skill's source is 'anthropics/skills' (a trusted source per the [TRUST-SCOPE-RULE]), these dependencies are considered safe and standard for the intended use case.
  • [COMMAND_EXECUTION] (SAFE): The provided Python snippet saves a generated image to the local file system ('design.png'). This is consistent with the primary purpose of the skill and does not involve arbitrary command execution or shell injection.
  • [PROMPT_INJECTION] (SAFE): The instructions focus entirely on design principles and technical implementation. No attempts to override system prompts or bypass safety filters were detected.
  • [DATA_EXFILTRATION] (SAFE): There are no network operations, hardcoded credentials, or access requests to sensitive file paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:44 PM