illustration
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill instructions and templates revealed no security vulnerabilities, malicious patterns, or unauthorized access attempts.
- [PROMPT_INJECTION]: The skill uses structured templates for prompt construction to control artistic style and scene content. These patterns do not attempt to override agent safety filters or system instructions.
- [DATA_EXFILTRATION]: No network operations, API calls, or access to sensitive local files are defined in the skill content.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any downloads of external packages, scripts, or remote content. References to models like BiRefNet are mentions of technical methodologies rather than executable installation commands.
Audit Metadata