google-ad-scraper

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's documentation and requirements specify the installation of the 'requests' Python package, which is a standard and highly-trusted library for HTTP requests.
  • [PROMPT_INJECTION]: The skill retrieves untrusted content from external advertisements (headlines, descriptions, and previews), which constitutes an indirect prompt injection surface.
  • Ingestion points: Data is fetched from the Google Ads Transparency Center via Apify's dataset API in scripts/search_google_ads.py.
  • Boundary markers: The script does not employ specific delimiters or warnings to separate the retrieved ad content from the rest of the agent's context.
  • Capability inventory: The script performs network operations to the vendor's proxy (app.gooseworks.ai) and Apify, but does not interact with the local filesystem (beyond reading environment variables) or execute local system commands.
  • Sanitization: The skill performs minimal sanitization, primarily truncating strings and replacing newlines for summary display, passing the core advertisement text through to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — google-ad-scraper