define-art-direction
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, focusing on translating visual intent into documented rules. Analysis across all 11 threat categories found no security issues.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve reading external data (references, existing contracts, and studies). While this creates an ingestion surface for indirect prompt injection, the risk is minimal as the skill does not include any commands for code execution, file system modification, or network requests that could be hijacked by malicious content in those references.
Audit Metadata