MinerU Document Extractor

v0.2.1

MinerU document extraction — the all-in-one CLI and agent skill for converting PDFs, scanned documents, images, Word (DOC/DOCX), PowerPoint (PPT/PPTX), and w...

5· 1.4k·2 current·2 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The skill name/description, required binary (mineru-open-api), and install specs (npm package and go install from a GitHub repo) all match the stated purpose of document extraction and web crawling. No unrelated binaries or unexplained credentials are requested.
Instruction Scope
The SKILL.md instructs the agent to run mineru-open-api commands (flash-extract/extract/crawl), optionally authenticate (mineru-open-api auth / MINERU_TOKEN), and to crawl HTTP/HTTPS URLs. This is expected for a document-extraction tool, but it does mean files and web pages are uploaded to MinerU's service (mineru.net) — a privacy/exfiltration risk inherent to the functionality.
Install Mechanism
Install methods use standard registries: npm package 'mineru-open-api' and go install from github.com/opendatalab/.... No arbitrary download URLs, extract steps, or obscure shorteners are used in the install spec.
Credentials
No required environment variables are declared. An optional MINERU_TOKEN is used for authenticated 'extract' and 'crawl' modes and is stored in ~/.mineru/config.yaml or provided via --token, which is proportionate to the feature set.
Persistence & Privilege
The skill is not forced-always; it's user-invocable and can be invoked autonomously (platform default). The only persistence noted is storing the MinerU token in ~/.mineru/config.yaml via the CLI auth flow, which is expected for CLI tools.
Assessment
This skill appears to do what it says, but it uploads documents and crawled pages to MinerU's service (mineru.net). Before installing: verify the npm package and GitHub repo authorship and reputation, review MinerU's privacy/security policy, avoid sending highly sensitive or regulated documents unless you trust the service, be aware that the token (MINERU_TOKEN) will be stored in ~/.mineru/config.yaml if you use the auth flow, and consider testing in an isolated environment if you have doubts.

Like a lobster shell, security has layers — review code before you run it.

latestvk978yq8s40repws2fr8w683zk184dq5f

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

📄 Clawdis
Binsmineru-open-api

Install

Install via npm
Bins: mineru-open-api
npm i -g mineru-open-api
Install via go install
Bins: mineru-open-api

Comments