imax-portrait
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No evidence of malicious behavior, obfuscation, or sensitive data access was found. The skill defines clear, task-specific instructions for an image processing workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-uploaded image data for character and lighting analysis, representing a potential surface for indirect prompt injection. However, the risk is categorized as safe because the agent's capabilities are restricted to image generation tools, which prevents the exfiltration of sensitive data or unauthorized system changes.
- Ingestion points: SKILL.md (logic for identifying content within user-uploaded images).
- Boundary markers: No specific boundary markers or instructions to ignore embedded content are defined for the image analysis step.
- Capability inventory: Limited to image generation and editing tools.
- Sanitization: No explicit sanitization of input image content or metadata is specified.
Audit Metadata