lit-synthesis

Warn

Audited by Snyk on Feb 16, 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 ingests full-text PDFs and annotations from a user's Zotero library via Zotero MCP (e.g., zotero_get_item_metadata, zotero_get_annotations and Zotero's "Find Available PDF"/Web API), which can pull arbitrary, public or user-provided web content that the agent will read and interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:28 AM