baoyu-article-illustrator

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs benign file system checks using shell commands like test -f to verify the existence of configuration files (EXTEND.md) and reference images. This is used for internal workflow logic and configuration management.
  • [PROMPT_INJECTION]: The skill processes user-provided articles to generate image prompts, which is an inherent part of its functionality. While this creates a surface for indirect instructions, the use of structured templates for prompt construction mitigates the risk of arbitrary instruction execution.
  • [SAFE]: The skill maintains persistent user settings in a local directory (.baoyu-skills/ or ~/.baoyu-skills/), which is a standard and safe practice for providing a consistent user experience across different projects.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 06:31 AM