prompt-to-design
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to install necessary Python dependencies (Pillow and NumPy) and execute generated design scripts using the Python interpreter. This is a legitimate functional requirement for the skill's purpose.
- [DYNAMIC_EXECUTION]: The agent is required to generate and execute Python code at runtime to create graphics. This execution is scoped to the provided local library (render.py) and does not involve downloading untrusted remote code or using dangerous system primitives.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts to generate design elements. While this creates an attack surface for instructions embedded in data, the risk is negligible as the output is a static image and the rendering engine has no access to sensitive system resources or network capabilities.
Audit Metadata