Research Ideation

Warn

Audited by Snyk on Feb 18, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly performs WebSearch across public academic sites (arXiv, Google Scholar) and uses Zotero MCP functions (add_items_by_doi, find_and_attach_pdfs, get_item_fulltext) to import and read open web PDFs, so the agent fetches and interprets untrusted third‑party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 18, 2026, 02:52 PM