Ocr Local 1.0.0

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

This skill appears coherent and does what it claims: it runs Tesseract.js locally on a provided image. Before installing, be aware that (1) npm install will download tesseract.js and its dependencies from the public registry and may run package lifecycle scripts (opencollective-postinstall is present in deps) — run npm install in a controlled environment or inspect dependencies if you are cautious; (2) Tesseract language data will be downloaded on first run (~20MB/language) so the process needs network access unless you pre-provision the traineddata files; (3) there is no credential or secret access requested. If you want maximum safety, audit the tesseract.js package and its postinstall behavior, or vendor the dependency and the language files yourself and run the script offline. Additionally, note a minor metadata inconsistency (ownerId differs between registry metadata and _meta.json) — likely benign but worth noticing.

Type: OpenClaw Skill Name: ocr-local-1-0-0 Version: 1.0.0 The skill provides local OCR functionality using the legitimate Tesseract.js library. The implementation in scripts/ocr.js is straightforward, handling image path resolution and language selection without any signs of data exfiltration, malicious execution, or prompt injection. All files, including SKILL.md and the NPM configuration, align perfectly with the stated purpose of providing a local text recognition tool.