Tesseract Ocr
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: tesseract-ocr Version: 1.0.0 The skill bundle is designed to use the Tesseract OCR command-line tool, which is a legitimate utility. However, the `SKILL.md` instructions demonstrate executing `tesseract` with user-provided file paths and language codes. This inherently introduces a shell injection vulnerability if the OpenClaw agent does not properly sanitize user input before constructing and executing the `tesseract` command. While the skill itself does not contain malicious code or explicit prompt injection attempts, the direct exposure of a command-line interface with user-controlled arguments creates a high-risk scenario for potential Remote Code Execution (RCE) via shell injection, classifying it as suspicious due to this critical vulnerability risk.
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.
The user may need to install OCR software from their operating system package manager before the skill works.
The skill depends on installing external system packages, but this is a normal and disclosed setup step for using Tesseract OCR.
sudo apt-get install tesseract-ocr tesseract-ocr-chi-sim # macOS: brew install tesseract tesseract-lang
Install Tesseract only from trusted package repositories, and review package-manager prompts before approving installation.
The agent may run local OCR commands against image files the user provides or identifies.
The skill instructs the agent to run the local Tesseract CLI on user-provided image files. This command execution is central to the skill's OCR purpose and is not hidden or unrelated.
tesseract /path/to/image.png stdout -l chi_sim+eng
Use the skill on intended image files only, and check output file paths when saving OCR results.