baoyu-xhs-images

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8) during the processing of user content for image generation. Ingestion points: User-provided text or files saved to source.md in Step 1. Boundary markers: Prompt assembly logic in references/workflows/prompt-assembly.md lacks robust delimiters or 'ignore embedded instructions' markers for the content section. Capability inventory: The skill performs local filesystem writes and calls external image generation tools. Sanitization: No sanitization or filtering of the source content is documented before interpolation into prompts.
  • [COMMAND_EXECUTION]: The skill utilizes basic shell commands for environment configuration and preference management. It executes bash commands to verify the existence of the EXTEND.md file within the user home directory structure ($HOME/.baoyu-skills/) during the setup phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 02:39 PM