nature-literature-pipeline
Warn
Audited by Snyk on Jun 30, 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). Runtime workflow ingests outsider-authored free text from public scholarly sources (e.g., arXiv/OpenAlex/Crossref/Semantic Scholar) during the “SEARCH → FINE READ (Abstract-level or full-text)” stages, where fetched abstracts/full text are summarized and placed into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata