data-scraper-agent
Warn
Audited by Snyk on Jul 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In the required runtime workflow, the agent’s Step 3/Step 5 path scrapes outsider-controlled public website/API/RSS content via user-authored source modules (e.g.,
scraper/sources/*usingrequests/BeautifulSoup/RSS/Playwright) and then feeds that extracted text into Gemini prompts for enrichment inai/pipeline.py, enabling indirect prompt injection from the scraped page data.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata