paper-submission
Warn
Audited by Snyk on Jun 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Phase 2 requires WebSearch/WebFetch of public academic pages at runtime; the fetched page text/abstracts from those outsider-authored sources are then used to generate the novelty assessment that is fed into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata