MinerU Document Extractor

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill specifies the installation of the mineru-open-api CLI tool via NPM or Go from official vendor repositories on GitHub.
  • [COMMAND_EXECUTION]: The agent is directed to use the mineru-open-api command-line interface for document conversion, web crawling, and authentication tasks.
  • [DATA_EXFILTRATION]: Features like crawl and flash-extract allow the tool to fetch and process content from remote URLs as part of its document extraction workflow.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection due to its core functionality of ingesting and parsing untrusted external documents and web content.
  • Ingestion points: Processes local files such as PDFs and images, and crawls remote web pages.
  • Boundary markers: No specific delimiters or instructions to treat output as untrusted data are defined in the skill body.
  • Capability inventory: The skill uses the mineru-open-api tool for shell-based document processing.
  • Sanitization: No explicit sanitization or filtering of the extracted content is mentioned in the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:32 PM