deep-research
Warn
Audited by Snyk on Oct 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow uses search and scraping tools (Firecrawl and Exa) to fetch arbitrary web pages selected via search queries, which is a low-risk vector as the agent must actively search/fetch external content rather than ingesting a monitored feed.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata