MinerU PDF Parser Clawdbot Skill

Parse PDFs locally (CPU) into Markdown/JSON using MinerU. Assumes MinerU creates per‑doc output folders; supports table/image extraction.

This skill appears to do exactly what it claims: call a local MinerU CLI to parse PDFs into Markdown/JSON and write results to a local output folder. Before installing or running: (1) ensure you have a trustworthy MinerU CLI binary installed (the skill will run whatever MINERU_CMD points to), (2) be cautious if you set MINERU_EXTRA_ARGS or override MINERU_CMD — they can change the executed command or inject unexpected arguments, (3) run the skill on non-sensitive PDFs first to confirm output and behavior, and (4) be aware MinerU may use significant CPU and disk (models can be large). No credentials or network endpoints are required by the skill itself.

Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill The `scripts/mineru_parse.sh` script contains a shell injection vulnerability. The `MINERU_EXTRA_ARGS` environment variable is unquoted and word-split (`extra=( ${MINERU_EXTRA_ARGS} )`), and these split arguments are then passed to the `mineru` command. This allows an attacker to inject arbitrary shell commands (e.g., `MINERU_EXTRA_ARGS="; evil_command"`) which would be executed by the shell after the `mineru` command, enabling arbitrary command execution. While the skill itself does not explicitly instruct the agent to perform malicious actions, this risky capability presents a significant security vulnerability.