PDF Utils

PDF Utils enables OCR of image-based PDFs, extraction of arXiv IDs from text or OCR output, and scriptable PDF tasks like merging, splitting, and rendering.

This skill appears coherent and implements what it claims. Before installing/using: (1) review and run the scripts on unprivileged/sample PDFs to confirm behavior; (2) be aware OCR requires installing the tesseract binary and language packs (SKILL.md suggests brew); (3) the extract_refs download option uses curl to fetch PDFs from arxiv.org — only enable downloads when you want network activity and ensure you trust the source; (4) the scripts write output files (papers/, temporary PNGs, OCR text) in locations you specify — run them in directories you control; (5) if you need higher assurance, inspect or run the included tests and review the small subprocess calls (curl, tesseract) which are expected for this functionality.

Type: OpenClaw Skill Name: pdf-utils Version: 1.0.1 The pdf-utils skill is a legitimate utility for PDF processing, OCR, and arXiv reference extraction. It uses standard libraries like PyMuPDF (fitz) and Tesseract (pytesseract) for its core functionality. While it uses subprocess.run to invoke 'curl' for downloading papers and 'tesseract' for language checks, it does so safely by passing arguments as a list rather than a shell string, and the inputs (arXiv IDs) are validated via strict regex patterns. No evidence of data exfiltration, persistence, or malicious prompt injection was found.