skills/lanej/dotfiles/canvas-design/Gen Agent Trust Hub

canvas-design

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for the creative generation of visual art and design philosophies. A thorough analysis of its instructions and support files confirms it adheres to its stated purpose without introducing security risks.
  • [PROMPT_INJECTION]: The instructions use assertive steering techniques, such as defining mandatory craftsmanship standards and pre-loading a refinement stage (simulating user feedback for a "masterpiece"). While these are strong behavioral constraints, they are used to ensure artistic quality and do not attempt to override safety protocols or extract system-level prompts.
  • [DATA_EXFILTRATION]: No network-enabled operations or attempts to access sensitive system files (e.g., credentials or environment variables) were found. The skill's activities are confined to creating local Markdown, PDF, and PNG files.
  • [REMOTE_CODE_EXECUTION]: The skill does not contain logic for downloading and executing external scripts. It provides a directory of font license files (canvas-fonts/), indicating that the design process is intended to use approved local or standard system resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 07:26 PM
Security Audit — agent-trust-hub — canvas-design