genimage

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script genimage.py with arguments provided by the user, such as prompt text and image file paths.
  • [SAFE]: No malicious patterns, hardcoded secrets, or unauthorized network behaviors were identified. The use of environment variables and structured CLI flags aligns with secure implementation.
  • [SAFE]: The skill processes user-supplied text to generate images, which serves as a surface for indirect prompt injection. * Ingestion points: User input in the --prompt argument in SKILL.md. * Boundary markers: None present in the instructions. * Capability inventory: Subprocess call to a Python script for API interaction and file writing. * Sanitization: Not explicitly described in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:58 PM