research-zotero
Warn
Audited by Snyk on Jul 17, 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). Outsider-authored free text from the user’s Zotero library is fetched at runtime via the Zotero Web API (e.g.,
scripts/fetch_zotero_items.py→_zotero.fetch_paginated_items()→api_get_json()), then written intozotero-items.json/zotero-sync.mdas readable JSON/Markdown that downstream LLM steps may ingest.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata