pdf-parser-mineru
v1.0.2PDF document parsing tool based on local MinerU, supports converting PDF to Markdown, JSON, and other machine-readable formats.
⭐ 0· 1.4k·1 current·1 all-time
by@baokui
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the included files: SKILL.md documents running MinerU and the repository provides an install script and a Python wrapper that invokes the mineru CLI. Required capabilities (MinerU installation, Python) are proportional to the stated parsing functionality.
Instruction Scope
Runtime instructions and the Python script stay within the skill's scope: they accept an absolute file path and output directory, run a local mineru CLI process, and read/return generated files. The script sets a couple of local env vars to control device selection for the subprocess but does not read or transmit unrelated system secrets or contact hidden endpoints itself. Note: mineru (the third-party tool) may perform network activity or model downloads — that behavior is external to the skill and should be reviewed if you need offline guarantees.
Install Mechanism
There is no platform install spec in registry metadata, but an included install.sh performs pip and 'uv pip install -U "mineru[all]"'. Installing MinerU via PyPI is expected here; it's a moderate-risk operation (pulling packages from PyPI and possibly downloading models/data at runtime). No obscure URLs, shorteners, or direct archive downloads are used in the provided scripts.
Credentials
The skill requests no environment variables or credentials. The code sets PYTORCH_ENABLE_MPS_FALLBACK and MPS_DEVICE locally for the mineru subprocess (device control only). There are no requests for unrelated secrets or config paths.
Persistence & Privilege
Skill flags are standard (always: false, agent invocation allowed). The package does not request permanent system changes or modify other skills' configs. install.sh and the Python script only install MinerU and run it; they do not attempt to persist credentials or enable automatic always-on behavior.
Assessment
This skill is internally coherent: it installs MinerU and runs the mineru CLI to convert PDFs to Markdown/JSON. Before installing, consider the following: (1) mineru is a third-party PyPI package — review its project page and dependencies and prefer installation into an isolated virtual environment or container; (2) MinerU may download models or contact network endpoints at install/time or runtime — if you need offline/sandboxed processing, verify or block network access; (3) the skill requires absolute file paths and can read any PDF you point it at — avoid supplying sensitive documents to untrusted third-party binaries; (4) the included install.sh is safe-looking but will run pip installs and assumes Python 3.10–3.13; run it manually rather than automatically if you want to inspect it first. If you want stronger assurance, review the mineru package source and any model download behavior before use.Like a lobster shell, security has layers — review code before you run it.
latestvk97fj94edr2v3jpvk9ajgzhe6x80zd8b
License
MIT-0
Free to use, modify, and redistribute. No attribution required.