pypdf

Extract text, metadata, and pages from PDF files using pypdf. Use for tasks such as reading PDF content, extracting specific pages, splitting or merging PDFs...

Security Scan

The skill does what it says: a small CLI wrapper around the pypdf library for local PDF operations; its files, instructions, and requirements are coherent and proportionate to that purpose.

Purpose & Capability

Name and description match the included CLI (scripts/pypdf_cli.py) and the SKILL.md commands. Required binary (python3) is appropriate and no unrelated credentials, binaries, or config paths are requested.

Instruction Scope

SKILL.md instructs the agent to run the included script against local PDF paths and to install pypdf if missing. The runtime instructions only reference local file paths and stdout/stderr; there are no steps that read unrelated system files, environment variables, or send data to external endpoints.

Install Mechanism

There is no formal install spec. The SKILL.md recommends installing the pypdf Python package with pip when missing — this is expected but means network access to PyPI will be required to satisfy dependencies. That is normal for Python tools but carries the usual supply-chain considerations of pip packages.

Credentials

The skill requires no environment variables, credentials, or config paths. All file I/O is limited to user-provided input/output paths, which is proportionate to the skill's stated PDF-processing purpose.

Persistence & Privilege

The skill does not request always: true, does not modify other skills or global agent config, and has no built-in persistence. Agent autonomous invocation settings are the platform defaults and not a special privilege here.

Assessment

This skill is coherent and appears to only operate on local PDFs using the included Python script. Before installing/using: (1) confirm you are comfortable running Python code on local PDF files (the script will read and write files you point it at); (2) note that if pypdf is missing the SKILL.md tells you to pip install pypdf — installing from PyPI requires network access and the usual supply-chain trust in that package; (3) if you will process untrusted PDFs, consider running the tool in an isolated/sandboxed environment because PDF parsers have historically had security bugs; and (4) if you want extra assurance, you can review the provided scripts/pypdf_cli.py (its source is small and readable) or run it on non-sensitive test files first.

Use scripts/pypdf_cli.py for deterministic PDF operations instead of ad-hoc pypdf snippets.

Workflow

1. Confirm the PDF file path is accessible locally.
2. Run the desired command (inspect, extract-text, extract-pages, merge, split, rotate).
3. Inspect text output or the resulting PDF file.

Command Guide

• Inspect metadata and page count:
  • python scripts/pypdf_cli.py info --input <file.pdf>
• Extract all text:
  • python scripts/pypdf_cli.py extract-text --input <file.pdf>
• Extract text from specific pages (0-indexed):
  • python scripts/pypdf_cli.py extract-text --input <file.pdf> --pages 0 1 2
• Split PDF into individual pages:
  • python scripts/pypdf_cli.py split --input <file.pdf> --output-dir <dir/>
• Extract a page range into a new PDF:
  • python scripts/pypdf_cli.py extract-pages --input <file.pdf> --pages 0 1 2 --output <out.pdf>
• Merge multiple PDFs:
  • python scripts/pypdf_cli.py merge --inputs <a.pdf> <b.pdf> <c.pdf> --output <merged.pdf>
• Rotate pages:
  • python scripts/pypdf_cli.py rotate --input <file.pdf> --angle 90 --output <rotated.pdf>
  • --angle must be 90, 180, or 270.
  • Optionally restrict to specific pages with --pages 0 2.

Operational Rules

• Pages are always 0-indexed in all commands.
• For extract-text, output goes to stdout; redirect to a file when needed.
• Require explicit --output for commands that write a new PDF.
• Install dependency if missing: pip install pypdf.