image-ocr
AdvisoryAudited by VirusTotal on Apr 15, 2026.
Overview
Type: OpenClaw Skill Name: jpg-ocr-stat-image-ocr Version: 0.1.0 The skill bundle provides standard Optical Character Recognition (OCR) functionality using the Tesseract engine and the Pillow library. The code in SKILL.md implements typical image preprocessing, batch processing, and multi-pass OCR strategies without any signs of malicious intent, data exfiltration, or unauthorized system access.
Findings (0)
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.
If the user or agent installs missing OCR dependencies separately, security depends on choosing trusted package sources and versions.
The skill's visible instructions require external OCR/Python dependencies, but the registry provides no install specification or pinned provenance for them.
Source: unknown; Homepage: none ... No install spec — this is an instruction-only skill.
Install Tesseract, pytesseract, and Pillow only from trusted sources, and pin versions for repeatable use.
Selecting a broad folder could extract text from more local images than intended, including receipts, screenshots, or forms.
The documented batch workflow can read every supported image in a chosen directory and write OCR results to a file.
def process_image_directory(directory_path, output_file):
"""Process all images in a directory and save results."""Use narrow, intentional input folders and review OCR output before sharing it elsewhere.