Docx Toolkit

PassAudited by ClawScan on May 1, 2026.

Overview

Docx Toolkit appears to be a straightforward local Word-document extraction tool, with normal cautions around installing Python dependencies and protecting extracted document contents.

This skill looks appropriate for local Word-document extraction. Before installing, use a trusted Python environment, consider pinning dependencies, run it only on documents you intend to process, choose explicit output folders, and protect extracted files or manifests that may contain sensitive information.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Installing dependencies could pull newer or different package versions than the author tested.

Why it was flagged

The skill asks users to install live, unpinned Python packages. These dependencies are expected for Word and image processing, but unpinned package installs depend on external package provenance at install time.

Skill content
pip3 install python-docx olefile Pillow
Recommendation

Install in a virtual environment and pin or review dependency versions if using this on sensitive documents.

What this means

Original extracted images may be compressed or changed if the command is run without a separate output folder.

Why it was flagged

The resize helper can modify existing image files when no output directory is provided. This is disclosed and purpose-aligned, but it can reduce image quality or replace originals.

Skill content
If output_dir is omitted, overwrites in place.
Recommendation

Use an explicit output directory when resizing images unless you intentionally want in-place compression.

What this means

Extracted text, images, and manifests may reveal confidential content such as contracts, certificates, or personnel information.

Why it was flagged

The tool can store surrounding document text and image classifications in a manifest. This is useful for review workflows, but it creates local derived context that may include sensitive information from the source document.

Skill content
image_manifest.json (when --context): maps each image to its context
Recommendation

Keep output folders private, review manifests before sharing them, and avoid sending extracted content to external services unless appropriate.