mineru

Warn

Audited by Snyk on Feb 25, 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.md shows the MinerU API accepts arbitrary http/https file URLs (e.g., the "url" parameter in https://mineru.net/api/v4/extract/task and the arXiv example https://arxiv.org/pdf/2410.17247), meaning the agent fetches and ingests untrusted public third‑party documents which it will read/interpret as part of its workflow, allowing those documents to influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 03:49 AM