qiaomu-mondo-poster-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted natural language prompts from users to generate optimized prompts for AI image generation models.
- Ingestion points: User-provided descriptions of posters, books, or albums (defined in natural language triggers in
SKILL.md). - Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions to prevent the agent from obeying instructions embedded within the user's content.
- Capability inventory: The skill facilitates network operations (via OpenAI/Anthropic API keys for image generation) and file system operations (saving generated images to
POSTER_OUTPUT_DIR). - Sanitization: No explicit sanitization or filtering of user input is described in the provided documentation.
- [SAFE]: The skill provides standard documentation for installation via a public package registry and correctly recommends the use of environment variables for API key management, which is a secure practice.
Audit Metadata