text-in-image
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code or patterns detected. The skill focuses on technical instructions for high-fidelity image generation.
- [EXTERNAL_DOWNLOADS]: The skill references
im.runware.aifor image assets. This is recognized as vendor-owned infrastructure belonging to 'runware'. - [DATA_EXFILTRATION]: There are no commands that access sensitive files (e.g., credentials, SSH keys) or transmit data to unauthorized external endpoints.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-defined text for image rendering. The instructions mandate the use of quotation marks to delimit this text, which serves as a boundary to ensure the image models treat the input literally, reducing the risk of accidental instruction following from processed data.
Audit Metadata