OCR Local V2

Extract text from images using Tesseract.js OCR (100% local, no API key required). Supports Chinese (simplified/traditional) and English.

Security Scan

The skill's code, instructions, and dependencies are consistent with a local Tesseract.js OCR tool; no unexpected credential requests or hidden network endpoints are present beyond the expected language-data downloads.

Purpose & Capability

Name/description, package.json, SKILL.md, and scripts/ocr.js all align: a Node-based Tesseract.js OCR utility for Chinese/English. Required binary (node) and the tesseract.js dependency are appropriate and expected.

Instruction Scope

Runtime instructions and the script only read the user-supplied image path and produce text/JSON output. SKILL.md and README explicitly warn that language data (~20MB per language) will be downloaded on first run — this implies network activity to fetch traineddata, which is expected for Tesseract.js but is an external network side-effect users should know about.

Install Mechanism

The registry entry has no formal install spec, but SKILL.md metadata and package.json declare installing tesseract.js via npm. This is a standard install path (npm dependency). No arbitrary URL downloads or archive extraction in the skill bundle itself; runtime traineddata fetches are performed by tesseract.js (expected).

Credentials

The skill requests no environment variables or credentials. It does not access system config paths. No disproportionate secret or credential requests were found.

Persistence & Privilege

always is false (default). The skill does not request persistent system-wide privileges or modify other skills. It is user-invocable and may be invoked by the agent, which is the platform default.

Assessment

This appears to be a legitimate local OCR skill. Things to consider before installing: (1) npm will install tesseract.js (check the dependency/version). (2) On first run Tesseract.js will download language-traineddata (≈20MB per language) from a remote host — if you need to avoid network fetches or want to control the source, run in an environment where you can vet or pre-provision the traineddata. (3) The package metadata contains a minor owner/slug mismatch in _meta.json vs. registry metadata — likely benign but you may want to confirm the skill source (repository URL) if provenance matters. (4) Run in a sandbox if you need extra caution; otherwise the code is straightforward and only processes the image you provide.

OCR - Image Text Recognition (Local)

Extract text from images using Tesseract.js. 100% local run, no API key required. Supports Chinese and English.

Quick start

node {baseDir}/scripts/ocr.js /path/to/image.jpg
node {baseDir}/scripts/ocr.js /path/to/image.png --lang chi_sim
node {baseDir}/scripts/ocr.js /path/to/image.jpg --lang chi_tra+eng

Options

• --lang <langs>: Language codes (default: chi_sim+eng)

  • chi_sim - Simplified Chinese
  • chi_tra - Traditional Chinese
  • eng - English
  • Combine with +: chi_sim+eng

• --json: Output as JSON instead of plain text

Examples

# Recognize Chinese screenshot
node {baseDir}/scripts/ocr.js screenshot.png

# Recognize English document
node {baseDir}/scripts/ocr.js document.jpg --lang eng

# Mixed Chinese + English
node {baseDir}/scripts/ocr.js mixed.png --lang chi_sim+eng

Notes

• First run downloads language data (~20MB per language)
• Subsequent runs are cached locally
• Works best with clear, high-contrast images
• For handwritten text, accuracy may vary