long-form-article
Warn
Audited by Snyk on Nov 17, 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 Phase 2 research fans out to WebSearch, WebFetch, Exa and Firecrawl to read arbitrary studies and web pages, which the agent must actively search for and fetch, so outsider-authored text is exposed at low risk rather than medium.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata