design-image-prompt-engineer
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The provided script
scripts/run.shis a standard wrapper for executing the skill using a platform runner (run-skill.py). It does not perform any unauthorized command execution or system modifications. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided visual concepts or tasks to generate prompts. While this represents an input surface for untrusted data, the skill has no dangerous capabilities such as file system access, network operations, or code execution that could be exploited via injection.
- Ingestion points: User tasks provided via CLI arguments or standard input.
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: None. The skill only produces text output.
- Sanitization: Not applicable as there are no downstream executable actions.
Audit Metadata