baoyu-cover-image

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to verify the presence of configuration files in the project-local and user-home directories ($HOME/.baoyu-skills/) to manage settings.
  • [PROMPT_INJECTION]: The skill processes article content to generate prompts for external image generation tools.
  • Ingestion points: Article text enters the context in Step 1 through file reads or direct input.
  • Boundary markers: The skill structures the generation prompt using markdown headers to separate content from design instructions.
  • Capability inventory: The skill uses shell commands and inter-skill communication to generate images.
  • Sanitization: There is no evidence of sanitization of the input text before its inclusion in the image generation prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 09:05 AM