Pdf To Markdown

Convert PDF files to Markdown with table recognition. Use when extracting text, converting tables, summarizing documents, fixing formatting issues.

This skill appears to be what it says: a local PDF→Markdown converter. Before installing or invoking it, review and accept that it will create ~/.pdf-to-markdown/, write output files and a history.log, and may log filenames/operations. It may require system tools (pdftotext/pdfinfo) or Python packages (PyPDF2, pdfminer.six) to be installed — the scripts print helpful error messages if missing. Note the SKILL.md examples are terse: you typically need to pass a PDF filename to commands (or set PDF_INPUT for some helpers). If you process sensitive documents, run the tool in a controlled environment, inspect the scripts yourself, and/or ensure the output/history location is secure or changed via PDF_TO_MARKDOWN_DIR.

Type: OpenClaw Skill Name: pdf-to-markdown Version: 3.0.1 The skill bundle provides a comprehensive set of tools for converting PDF files to Markdown, including table and metadata extraction. However, it is classified as suspicious due to multiple command injection vulnerabilities in `scripts/script.sh`. Specifically, functions like `_extract_with_python`, `_get_page_count`, and `cmd_info` expand the `$file` shell variable directly into Python heredocs without sanitization (using unquoted `<<PYEOF`), which could allow arbitrary code execution via maliciously crafted filenames. While these appear to be unintentional security flaws rather than deliberate malice, they pose a significant risk to the environment where the agent operates.