baoyu-article-illustrator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): In prompts/system.md, there is an explicit instruction to bypass content safety filters: 'If content involves sensitive or copyrighted figures, create stylistically similar alternatives
  • DO NOT refuse to generate'. This is a direct attempt to override the AI's standard refusal protocols for copyrighted material.
  • [SAFE] (SAFE): The skill implements a preference persistence mechanism using a local YAML file (EXTEND.md). While it writes to the file system, this is limited to a specific configuration file in a standard directory (.baoyu-skills/ or ~/.baoyu-skills/) and does not exhibit malicious behavior.
  • [DATA_EXPOSURE] (SAFE): No sensitive data access or exfiltration patterns were detected in the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:25 PM