deep-research
Warn
Audited by Snyk on Jul 30, 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). The “Deep Research” skill runtime explicitly performs web searches (multi-search-engine) and then uses an agent-browser to read full articles/PDFs from those search results, which can include outsider-authored content submitted via arbitrary web publishing/search poisoning.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata