generate-image

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated images from fal.ai CDN URLs. This is the primary intended function of the skill and uses the official provider's infrastructure.
  • [CREDENTIALS_UNSAFE]: The skill uses an API key (FAL_KEY) for authentication. It follows safe practices by instructing users to store this key in a local .env file (which is excluded via .env.example) or environment variables. The script specifically includes a rule to never print or log the API key value.
  • [COMMAND_EXECUTION]: The script uses Bun's native APIs and standard library for file operations (reading/writing images and JSON configs) and network requests. It does not spawn arbitrary shell commands or execute untrusted code.
  • [DATA_EXFILTRATION]: Network operations are restricted to official fal.ai domains (api.fal.ai, queue.fal.run, rest.fal.ai) for the purpose of image generation and management. No sensitive user data is sent to unauthorized third parties.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 01:39 PM
Security Audit — agent-trust-hub — generate-image