python-pipeline
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The pipeline reads arbitrary URLs from CSV in process_batch and uses Dispatcher/fetch_with_rate_limit (requests.get) and SocialProcessor/ArticleProcessor to fetch public web pages (and Google Sheets via SheetsService.get_worksheet/get_all_records), then feeds that untrusted, user-generated content into the AIService/Gemini for analysis, exposing the agent to indirect prompt injection.
Audit Metadata