google-ad-scraper

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to install the 'requests' library using pip. This is a standard dependency for performing the script's intended network operations.
  • [COMMAND_EXECUTION]: The skill provides documentation and examples for executing a local Python script ('search_google_ads.py') to perform search and scraping tasks.
  • [DATA_EXFILTRATION]: The script performs network operations to 'api.apify.com' to trigger scraping runs and retrieve datasets. Apify is a well-known service for web automation and data extraction, and these calls are necessary for the skill's functionality.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted content (ad headlines, descriptions, and text) from the Google Ads Transparency Center.
  • Ingestion points: Data is fetched from the Apify API in 'scripts/search_google_ads.py' and returned to the agent.
  • Boundary markers: There are no boundary markers or instructions to the agent to treat the scraped content as untrusted data.
  • Capability inventory: The skill has the capability to perform network requests via the 'requests' library and interact with remote scraping actors.
  • Sanitization: The script does not perform any sanitization, escaping, or validation of the text scraped from external ads before presenting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 01:07 PM