ai-paper-reader

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and processes arbitrary external papers (e.g., "paper.pdf" via functions like smart_extract_figures/extract_embedded_images and crop_figure) and even includes MCP connectors (Notion/filesystem) for pulling documents, so it will read untrusted third‑party content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:45 PM