image-ocr
PassAudited by ClawScan on May 10, 2026.
Overview
This is a straightforward OCR instruction skill, with minor cautions around local image batch processing and undeclared OCR dependencies.
This skill appears safe for normal OCR use. Before installing or using it, make sure any OCR dependencies come from trusted sources, and only point it at images or folders you actually want converted to text.
Findings (2)
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.