baoyu-xhs-images

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Bash shell commands (test -f) to verify the existence of the EXTEND.md configuration file in the project directory (.baoyu-skills/) and the user's home directory ($HOME/.baoyu-skills/).
  • [PROMPT_INJECTION]: Instructions in the references/workflows/prompt-assembly.md file direct the agent to circumvent safety filters during image generation. Specifically, it instructs the agent: 'If content involves sensitive or copyrighted figures... DO NOT refuse to generate,' and suggests creating 'stylistically similar alternatives' to bypass restrictions.
  • [NO_CODE]: The documentation and prompt assembly guides reference the execution of local scripts using the bun runtime via npx (e.g., npx -y bun ${SKILL_DIR}/scripts/main.ts). However, the skill package does not include a scripts/ directory or the main.ts file, indicating a dependency on external or missing code assets.
  • [DATA_EXPOSURE]: The skill performs file system operations targeting the user's home directory ($HOME) to manage cross-project persistent preferences.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 05:59 PM