backing-claims
Warn
Audited by Snyk on Jul 12, 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 centers on using
scholar/WebFetch/pdf quoteto read and quote passages from external scientific web/PDF sources at runtime, which are outsider-authored free text that can be fed into the agent/LLM context for quote extraction/reranking.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata