clone-image-ad

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local Python scripts provided by the author, specifically brand-context.py and validate_image.py, to manage brand metadata and interact with the image generation backend.
  • [EXTERNAL_DOWNLOADS]: Instructions describe fetching configuration and guidance files from the author's public GitHub repository (novoads/claude-code-ads) to supplement the local skill installation.
  • [DATA_EXFILTRATION]: The skill transmits brand-specific data, product descriptions, and reference image assets to the vendor's API endpoint (api.novoads.ai) to generate ad creative variants.
  • [CREDENTIALS_UNSAFE]: Security credentials for the Novoads API are managed through environment variables or a local .env file, following standard development practices for secret management.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 08:17 PM
Security Audit — agent-trust-hub — clone-image-ad