Img2md

Image to Markdown - extract text from images (PNG, JPG, WebP) to Markdown with OCR. Use when reading text from screenshots, photos, scanned pages, or any ima...

Security Scan

The skill's requirements and instructions align with an OCR-to-Markdown helper that calls the MinerU CLI; it mainly delegates work to a third-party CLI which uploads images to MinerU's cloud.

Purpose & Capability

The name/description (image → Markdown OCR) matches the declared binary dependency (mineru-open-api) and the SKILL.md commands (mineru-open-api flash-extract). No unrelated credentials, tools, or config paths are requested.

Instruction Scope

SKILL.md only instructs using the mineru-open-api CLI on local files or URLs and to return OCR output in the user's language. It explicitly states images are uploaded to MinerU's cloud for processing, which is consistent with the stated purpose but does mean user images are transmitted off-host.

Install Mechanism

Installation options are npm/uv/go installs of a mineru-open-api CLI or manual download from mineru.net. These are common distribution channels; no obscure shorteners or raw binary downloads are used. Installing will place a third-party CLI on the system and allow execution of that binary—verify trust in the package/source before installing.

Credentials

The skill requests no environment variables, credentials, or config paths. The SKILL.md mentions optional auth for advanced usage but does not require secrets for the basic flash-extract flow, which is proportionate to its function.

Persistence & Privilege

always is false and there is no attempt to modify system/agent-wide config. The skill does require installing a CLI binary but does not demand persistent elevated privileges in its metadata.

Assessment

This skill is internally consistent: it runs a third-party CLI (mineru-open-api) to OCR images and uploads images to MinerU's cloud for processing. Before installing or using it, consider: (1) Privacy — images (including screenshots or photos with sensitive content) will be transmitted to an external service; avoid sending sensitive images unless you trust MinerU's policy. (2) Trust the CLI package — review the npm package and the GitHub repo (the go install target) or inspectorily inspect the installer before installing to ensure it is legitimate. (3) Runtime autonomy — the skill can be invoked by the agent by default; if you want to prevent unexpected uploads, restrict agent autonomy or only invoke the skill manually. (4) For batch or higher-precision workflows the SKILL.md mentions auth is available; treat any credentials you supply to that CLI as sensitive. If you want more assurance, request the upstream package source code or a checksum for the distributed binary before installing.

Img2MD - Quick Image OCR to Markdown

Extract text from images to Markdown using MinerU Open API. No API key required.

Quick Start

# Img2MD - Quick Image OCR to Markdown
mineru-open-api flash-extract screenshot.png

# Img2MD - Quick Image OCR to Markdown
mineru-open-api flash-extract https://example.com/image.png

# Img2MD - Quick Image OCR to Markdown
mineru-open-api flash-extract photo.jpg -o ./output/

# Img2MD - Quick Image OCR to Markdown
mineru-open-api flash-extract scan.jpg --language en

Language Rule

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

Capabilities

• OCR text extraction from PNG, JPG, JPEG, 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 per image

When to Use

• User asks to "read", "extract", or "OCR" an image
• User shares a screenshot and asks what it says
• User wants text from a photo of a document or whiteboard
• User needs image content converted to Markdown

CLI Reference

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

Data Privacy

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

Notes

• Output is Markdown text extracted via OCR
• For higher precision or batch processing, use mineru-open-api extract (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