krea2-txt2img
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown documentation describing ComfyUI workflows. It does not contain any executable scripts, tool definitions, or automated commands that would execute on the agent's host environment.
- [EXTERNAL_DOWNLOADS]: The documentation references external models and LoRAs from community mirrors and provides instructions for installing PyTorch from the official PyTorch repository. These references are informative and consistent with the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to work with JSON files for structured prompt building. While this establishes a data ingestion surface, the documentation includes best practices for verifying image output and managing prompt fields to maintain consistency and prevent content leakage between sessions.
Audit Metadata