When dealing with text within an image, the system automatically recognizes it as an OCR (Optical Character Recognition) task and applies the corresponding capabilities.

OCR (Optical Character Recognition) tool using Tesseract for extracting text from images. Use when: (1) processing screenshots, charts, or documents in image...

This skill appears to do exactly what it claims: run Tesseract locally and parse the resulting text. Before installing, ensure you have (or want) a local Tesseract installation and any required language packs (chi_sim) for Chinese OCR. Review and, if desired, run the included test_ocr.py to verify behavior on sample images. Be mindful of privacy: OCR will read any image you feed it (including potentially sensitive content) and produce plain-text output; do not point it at images you don't want converted or stored. If you deploy this in an automated agent, note the agent can invoke local tesseract commands—there are no network exfiltration steps in the provided code, but still avoid giving it images that contain secrets you wouldn't want processed.

Type: OpenClaw Skill Name: ocr-tool Version: 1.0.0 The ocr-tool skill bundle is a legitimate utility designed to wrap the Tesseract OCR engine for text extraction from images, specifically optimized for financial announcements and charts. The bundle includes a Bash script (ocr.sh), a Python script (ocr_extract.py), and comprehensive documentation (SKILL.md) that align perfectly with its stated purpose. Analysis of the code and instructions found no evidence of malicious intent, data exfiltration, or unauthorized command execution; the use of subprocesses and shell commands is appropriate for interfacing with the Tesseract CLI tool.