create-image-fal

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: Reads authentication tokens and configuration from the vendor's local credentials file located at ~/.gooseworks/credentials.json. This is used to authorize requests to the image generation proxy and is standard behavior for the author's ecosystem.
  • [EXTERNAL_DOWNLOADS]: Downloads generated image assets from the FAL AI media distribution network (*.fal.media) to the local file system.
  • [PROMPT_INJECTION]: Ingests image generation prompts via the --payload argument. This represents a standard surface for indirect prompt injection common to generative AI tools, but is the primary intended function of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 09:42 AM
Security Audit — agent-trust-hub — create-image-fal