image-gen

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md guide the agent to execute a local Python script (generate_image.py) to interact with the image generation service.
  • Evidence: python3 "$SKILL_PATH/scripts/generate_image.py" "<提示词>"
  • [EXTERNAL_DOWNLOADS]: The Python script makes a network request to https://doubaoya.com/api/skills/gpt-image-gen/invoke using the standard urllib library. This is a functional requirement for the skill to communicate with the vendor's API.
  • Evidence: ENDPOINT = "https://doubaoya.com/api/skills/gpt-image-gen/invoke" in scripts/generate_image.py.
  • [CREDENTIALS_SAFE]: The skill follows security best practices by reading the API key from an environment variable (DOUBAOYA_API_KEY) rather than hardcoding it or accepting it as a command-line argument that might be logged.
  • Evidence: api_key = os.environ.get("DOUBAOYA_API_KEY") in scripts/generate_image.py.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:20 PM
Security Audit — agent-trust-hub — image-gen