qiaomu-mondo-poster-design

Warn

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions specify installation via npx skills add joeseesun/qiaomu-mondo-poster-design. This fetches code from a third-party source that is not verified as a well-known service or trusted organization.
  • [COMMAND_EXECUTION]: The documentation includes shell commands for environment configuration and Python scripts for batch image processing. These scripts use the os and PIL modules to manage file paths and save generated images locally.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data.
  • Ingestion points: User-provided strings in prompt and external image files via input_image_path (SKILL.md).
  • Boundary markers: None identified in the prompt interpolation logic.
  • Capability inventory: The skill performs file system writes (img.save) and interacts with external LLM APIs (OpenAI/Anthropic) to generate and optimize prompts.
  • Sanitization: No validation or sanitization of user input is documented before it is passed to the image generation or prompt optimization workflows.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 17, 2026, 11:54 AM