pdf-parser-mineru

PDF document parsing tool based on local MinerU, supports converting PDF to Markdown, JSON, and other machine-readable formats.

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.

Type: OpenClaw Skill Name: pdf-parser-mineru Version: 1.0.2 The OpenClaw AgentSkills skill bundle for PDF parsing using MinerU is classified as benign. All files, including `SKILL.md`, `install.sh`, and `script/pdf_parser.py`, align with the stated purpose of converting PDFs to Markdown or JSON. The `install.sh` script uses standard Python package management tools (`pip`, `uv`) to install the `mineru` dependency without any suspicious remote execution or persistence mechanisms. Crucially, the `script/pdf_parser.py` uses `subprocess.run` with a list of arguments, which safely prevents shell injection vulnerabilities from user-controlled parameters like `file_path` and `output_dir`. There are no indications of prompt injection attempts, data exfiltration, unauthorized network activity, or other malicious behaviors.