film-image-generator

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the transformation of user-provided descriptions into structured prompts for an image generation service (MiniMax). This creates an ingestion point for untrusted data that influences downstream AI actions.\n
  • Ingestion points: User input via commands like /image [prompt], /concept [description], and /storyboard [scene] in SKILL.md.\n
  • Boundary markers: None provided in the documentation to distinguish between user input and system instructions for the image generator.\n
  • Capability inventory: The skill relies on the MiniMax tool for image generation based on user-supplied content.\n
  • Sanitization: No explicit validation, filtering, or escaping is mentioned for the interpolated user prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 02:03 AM