deeppapernote
Warn
Audited by Snyk on Jun 13, 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). Workflow step 3–4 (“acquire the PDF or full text” and “extract evidence”) can fetch and ingest full text/PDF from non-user-provided sources (e.g., DOI/arXiv/URL/open-access pages) at runtime, which is outsider-authored content that becomes LLM-readable prose in the synthesis bundle.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata