TLDR Tech / InfoSec
url-content-auditor (GitHub Repo)
Salesforce's url-content-auditor is a Python-based security auditing tool that systematically downloads images, PDFs, and video files from publicly accessible URLs and passes them through Google Gemini (gemini-2.0-flash-lite) to detect exposed PII, credentials, financial records, and confidential documents - outputting findings to a CSV audit report at approximately $0.00013 per image. It handles both direct HTTP downloads and JavaScript-rendered pages via Selenium, with configurable parallel workers, automatic sampling for large URL sets, and support for CSV or plaintext URL lists as input.
Read the full story