deep-research
Warn
Audited by Snyk on Sep 12, 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 agent ingests outsider-authored free text by performing web searches and fetching arbitrary web pages via Firecrawl and Exa MCP tools, which constitutes low risk as the agent must actively search or select URLs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata