Extract Tables From Pdf

Extract tables from PDF documents using MinerU's table detection engine. Identifies and extracts structured table data from both native and scanned PDFs. Fea...

Security Scan

The skill is internally consistent with its stated purpose: it wraps the mineru-open-api CLI and requires a MinerU token; the main practical risk is that documents will be sent to the MinerU service, so avoid uploading sensitive PDFs unless you trust that service.

Purpose & Capability

Name/description match what is required: the skill requires the mineru-open-api binary and a MINERU_TOKEN, which are exactly what a MinerU-based PDF table extractor would need.

Instruction Scope

SKILL.md instructs the agent to run mineru-open-api commands, authenticate with MINERU_TOKEN, and operate on local files or URLs. This is within scope, but the instructions imply the CLI will use the token to contact MinerU services — meaning PDF contents may be transmitted to an external service; that is expected but important for privacy.

Install Mechanism

Installers are standard: npm package and go install from a GitHub repo. Both are reasonable for a CLI tool. Note: installing npm packages can run lifecycle scripts, so review the package or install in a controlled environment if you need extra safety.

Credentials

Only a single service credential (MINERU_TOKEN) is required and is declared as the primary credential. That is proportional to the described remote-API usage. The skill does not request unrelated credentials or system paths.

Persistence & Privilege

Skill does not request always:true or elevated platform persistence. It is user-invocable and can run autonomously (platform default), which is normal for skills of this type.

Assessment

This skill appears to be what it says: a wrapper around the mineru-open-api CLI that requires a MINERU_TOKEN. Before installing or using it: 1) Confirm mineru.net and the GitHub repo look legitimate and review their privacy/security docs; 2) Assume PDFs you process may be uploaded to MinerU servers—do not send sensitive or regulated data unless you trust the service or have an on-prem/self-hosted alternative; 3) Prefer installing in an isolated environment (container or VM) and inspect the npm/go package source if you require higher assurance; 4) Limit and rotate the MINERU_TOKEN and avoid storing it in shared shells; 5) If you need purely local-only processing, verify the CLI actually supports local-only mode or find an offline tool. If you want me to, I can fetch the mineru-open-api npm package or GitHub repo and highlight any concerning code or publish scripts before you install.

Convert and extract content from .pdf using MinerU (mineru-open-api).

Install

npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Quick Start

# Extract tables from PDF (requires token)
mineru-open-api extract report.pdf -o ./out/

# With explicit table flag and OCR for scanned docs
mineru-open-api extract scanned.pdf --ocr --table -o ./out/

Authentication

Token required for extract and crawl:

mineru-open-api auth            # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable

Create token at: https://mineru.net/apiManage/token

Capabilities

• Supports local files and URLs
• Requires token (mineru-open-api auth or MINERU_TOKEN env)
• Supported input: .pdf
• Language hint with --language (default: ch, use en for English)
• Page range with --pages (where applicable)

Notes

• Table recognition requires extract with token. flash-extract does NOT support tables. Use --table flag (enabled by default).
• Output goes to stdout by default; use -o <dir> to save to file
• Binary formats (docx) require -o flag (cannot stream to stdout)
• All progress/status messages go to stderr
• MinerU is an open-source project by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU