chatgpt-image-ad

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands (curl) and a local Python helper script (generate_image.py) to interact with the image generation API for estimation, uploads, and generation tasks.\n- [EXTERNAL_DOWNLOADS]: The skill downloads generated image files from the vendor's official API endpoint (api.novoads.ai) and retrieves metadata through standard HTTP GET/POST requests.\n- [CREDENTIALS_UNSAFE]: Authentication is managed via a NOVOADS_API_KEY retrieved from a local .env file, which follows industry-standard security practices for local environment configuration and secret management.\n- [SAFE]: The skill implements several defensive measures, including model-locking to gpt-image-2, mandatory cost confirmation phases before generation, and the automatic application of safety suffixes to prompts to ensure layout and text fidelity.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 08:17 PM
Security Audit — agent-trust-hub — chatgpt-image-ad