hypothesis-generation
Warn
Audited by Snyk on Jun 26, 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 runtime workflow includes “Conduct Comprehensive Literature Search” using WebFetch/WebSearch to access PubMed/general web pages, and the fetched page text can be ingested into the agent’s LLM context as free-form prose (public web content category via runtime browsing/scraping).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata