MinerU Doc Parser

ReviewAudited by ClawScan on May 1, 2026.

Overview

MinerU Doc Parser appears purpose-aligned, but it relies on an external CLI/API that may process your documents or URLs and can use a MinerU token.

This skill looks coherent for AI document parsing. Before installing, verify the mineru-open-api package source, use it only with documents and URLs you are comfortable sending to MinerU, and configure a MinerU token only when you need advanced extract or crawl features.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Low

#ASI02: Tool Misuse and Exploitation

What this means

The agent can invoke the document parser on files or URLs and save results when you ask it to use the skill.

Why it was flagged

The skill authorizes the agent to run the MinerU CLI with arbitrary subcommands and arguments. This is scoped to one purpose-aligned CLI, but it can still process files, URLs, and output paths.

Skill content

allowed-tools: Bash(mineru-open-api:*)

Recommendation

Use the skill only on intended files and URLs, and review output locations before running batch or crawl operations.

Low

#ASI03: Identity and Privilege Abuse

What this means

A configured MinerU token could be used for API-backed parsing and may count against your MinerU account or plan.

Why it was flagged

Advanced MinerU features can use a service token supplied by flag, environment variable, or local config. This is expected for the API workflow, and no token leakage or hardcoding is shown.

Skill content

mineru-open-api auth                    # Interactive token setup
export MINERU_TOKEN="your-token"  # Or set via environment variable
Token resolution order: `--token` flag > `MINERU_TOKEN` env > `~/.mineru/config.yaml`.

Recommendation

Create and store the token only if you need advanced extract or crawl features, and remove or rotate it if the environment is shared.

Low

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

Installing the skill’s required CLI gives locally installed code the ability to run when the skill invokes it.

Why it was flagged

The skill installs an external CLI from package managers, and the Go example uses the latest version. This is normal for a CLI-based integration but means users depend on that package source.

Skill content

npm install -g mineru-open-api
...
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Recommendation

Verify the package source and publisher before installing, and prefer pinned or reviewed versions in sensitive environments.

Medium

#ASI07: Insecure Inter-Agent Communication

What this means

Private documents or URLs could leave your local machine for AI document processing.

Why it was flagged

The documented workflow uses MinerU's API-backed CLI for local files and URLs. Document contents or target URLs may be processed by the external MinerU service, and the shown artifact text does not describe privacy or retention boundaries.

Skill content

Works with local files and URLs.
...
Create token at https://mineru.net/apiManage/token, run `mineru-open-api auth`, then use `mineru-open-api extract`

Recommendation

Do not process confidential, regulated, or proprietary documents unless MinerU’s data handling terms are acceptable for your use case.