General OCR Struct
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This skill coherently runs local OCR on user-provided images and shows no exfiltration, persistence, credential use, or destructive behavior, but users should install its Python OCR dependency from a trusted source.
This appears safe for its stated offline OCR purpose. Before installing, make sure any Python dependency is installed from a trusted source, run it only on images you intend to OCR, and follow the skill's own guidance to review raw text before using structured results.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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.
The agent can extract text from local images you provide, including receipts, statements, or screenshots.
The skill instructs the agent to run a local OCR command against a supplied file path. This is central to the skill's purpose, but the image may contain sensitive personal or financial text, so invocation should remain user-directed.
python3 scripts/general_ocr.py raw /path/to/image.jpg
Use it only on files you intentionally select, and review the raw OCR output before using it in summaries or records.
A user may need to install or rely on a local Python OCR dependency that is not pinned or described in the skill package.
The script requires a third-party OCR package, while the provided install information has no install spec or pinned dependency details. This is expected for OCR but should be installed from a trusted source.
from rapidocr_onnxruntime import RapidOCR
Install RapidOCR/rapidocr_onnxruntime only from trusted package sources, preferably with a pinned version in a controlled Python environment.