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.ai for 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
Risk Level
SAFE
Analyzed
Jul 2, 2026, 04:08 PM
Security Audit — agent-trust-hub — text-in-image