mineru

Warn

Audited by Snyk on Feb 28, 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 accepts and processes arbitrary public URLs (see scripts/mineru_api.py and other scripts' --url/--urls-file options, references/api_reference.md POST /extract/task, and README sections stating "PDF Input: Local files, URLs"), sending those remote documents to the MinerU API and parsing their contents as part of its runtime workflow, thus exposing the agent to untrusted third‑party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 09:39 AM