why-tree
Warn
Audited by Snyk on Jul 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow’s Phase 1/2 “Web” research path (Exa/firecrawl) can fetch public web pages at runtime and inject their scraped free-text into agent prompts for branch generation/deepen/refute, creating an indirect prompt-injection risk from outsider-authored content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata