gpt-image-skill

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled Python script gpt_image.py to perform image generation and editing tasks.
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated images from the OpenAI API (or a user-defined custom API base). The download logic in gpt_image.py includes security guardrails such as timeouts and file size limits (50MB) to prevent resource exhaustion.
  • [EXTERNAL_DOWNLOADS]: The skill requires standard, well-known Python packages (openai, httpx, python-dotenv) from official registries for its operation.
  • [CREDENTIALS_UNSAFE]: The skill manages sensitive API keys by reading them from a .env file in the user's home directory or from environment variables, which is a standard and recommended practice for command-line tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 04:18 PM
Security Audit — agent-trust-hub — gpt-image-skill