deep-research
Warn
Audited by Snyk on Jul 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: 0.85). Yes—during Phase 3 “RETRIEVE”, the required workflow calls
scripts/bd_search.pyto scrape arbitrary URLs (brightdata scrape -f markdown), and the returned scraped page text is then used by the LLM in later phases (evidence loop) to generate the report.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata