Scan To Markdown

OCR document extraction - extract text from scanned documents, photos, and images using OCR. Use when reading scanned PDFs, photographed pages, handwritten n...

Security Scan

The skill's requirements and instructions are consistent with an OCR CLI wrapper that calls MinerU's cloud API; nothing requested is disproportionate to that purpose.

Purpose & Capability

The name/description (OCR extraction) match the declared binary dependency (mineru-open-api) and the listed install options (npm/uv/go). No unrelated credentials, binaries, or config paths are requested.

Instruction Scope

Runtime instructions call mineru-open-api flash-extract on local files or URLs and explicitly upload documents to MinerU's cloud for processing. This is expected for a cloud OCR service, but it means user data is transmitted externally — the skill does not attempt to read unrelated local files or environment variables.

Install Mechanism

Installation is provided via standard package managers (npm, uv, go install). These are expected for a CLI tool; installing npm/go packages runs third-party code on the host, which is normal but carries the usual supply-chain risk (not an incoherence with the skill purpose). No arbitrary download URLs or archive extraction were used.

Credentials

No environment variables or credentials are required for the advertised 'flash-extract' capability. The SKILL.md notes an optional auth flow for higher-precision features, which would then require credentials — that is documented and consistent.

Persistence & Privilege

Skill is not always-enabled and is user-invocable. It does not request elevated persistence or modify other skills' configurations.

Assessment

This skill appears to do what it says: it installs a MinerU CLI and uploads documents to MinerU's cloud for OCR. Before installing or using it, consider: (1) MinerU processes files remotely — don't upload highly sensitive documents unless you trust their privacy policy and terms (check https://mineru.net). (2) Installing npm/go packages runs third-party code on your machine; review the package source (or use sandboxing) if you have security concerns. (3) Note the documented limits (10MB/20 pages) and that higher-precision extraction requires explicit auth. If you need offline-only OCR for sensitive content, prefer a local tool (e.g., Tesseract) instead.

Scan to Markdown - OCR for Scanned Docs

Extract text from scanned documents and images using OCR via MinerU Open API. No API key required.

Quick Start

# Scan to Markdown - OCR for Scanned Docs
mineru-open-api flash-extract scanned.pdf

# Scan to Markdown - OCR for Scanned Docs
mineru-open-api flash-extract page-photo.jpg

# Scan to Markdown - OCR for Scanned Docs
mineru-open-api flash-extract https://example.com/scanned.pdf

# Scan to Markdown - OCR for Scanned Docs
mineru-open-api flash-extract scanned.pdf --language en

# Scan to Markdown - OCR for Scanned Docs
mineru-open-api flash-extract scanned.pdf -o ./output/

Language Rule

You MUST reply to the user in the SAME language they use. This is non-negotiable.

Capabilities

• OCR for scanned PDFs, photographed documents, images
• Supports PDF, PNG, JPG, WebP, BMP, TIFF
• Supports both local files and URLs directly
• Language hint with --language (default: ch, use en for English)
• No API key, no signup, no authentication
• Max 10MB / 20 pages per document

When to Use

• User asks to "OCR" a document or image
• User has a scanned PDF that needs text extraction
• User shares a photo of a page and wants the text
• User mentions "scan", "handwriting", or "recognize text"

CLI Reference

Run mineru-open-api flash-extract --help for all available options.

Data Privacy

• flash-extract uploads the document to MinerU's cloud API for processing and returns the result. No account or API key is required.
• Documents are processed in real-time and are not stored after extraction.
• For details, see https://mineru.net

Notes

• Best results with clear, high-resolution scans
• For higher precision OCR with full layout preservation, use mineru-open-api extract --ocr (requires auth via mineru-open-api auth)
• If the CLI cannot be installed via npm/uv/go, download it from https://mineru.net/ecosystem?tab=cli