← Back to Skills Marketplace
4768
Downloads
2
Stars
47
Active Installs
1
Versions
Install in OpenClaw
/install tesseract-ocr
Description
Extract text from images using the Tesseract OCR engine directly via command line. Supports multiple languages including Chinese, English, and more. Use this...
Usage Guidance
Install Tesseract only from trusted package managers, run OCR only on files you intend to process, and review output paths before saving results. The skill is local-command based, but its behavior is disclosed and proportionate to OCR.
Capability Analysis
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.
Capability Assessment
Purpose & Capability
The stated purpose is extracting text from images, and the documented capability is limited to Tesseract OCR commands for image input, language selection, stdout, or an optional output file.
Instruction Scope
The skill uses local command execution with user-chosen file paths and language codes, which is expected for a CLI OCR skill; the artifact does not include a wrapper script or evidence of hidden command construction.
Install Mechanism
It asks users to install Tesseract and language packs through apt or Homebrew, including sudo on Debian/Ubuntu; this is disclosed and purpose-aligned but depends on trusted system package sources.
Credentials
No credentials, tokens, network APIs, broad indexing, unrelated file access, or external data transmission are requested.
Persistence & Privilege
No persistence, background agents, privilege retention, account access, or autonomous mutation behavior is described.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tesseract-ocr - After installation, invoke the skill by name or use
/tesseract-ocr - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the tesseract-ocr skill.
- Extract text from image files using the native Tesseract command line tool.
- Supports multiple languages, including Chinese, English, Japanese, and Korean.
- No Python or other language-specific dependencies required; works directly via CLI.
- Detailed usage examples provided for language selection and output options.
- Guidance on required system dependencies and language pack installation.
Metadata
Frequently Asked Questions
What is Tesseract Ocr?
Extract text from images using the Tesseract OCR engine directly via command line. Supports multiple languages including Chinese, English, and more. Use this... It is an AI Agent Skill for Claude Code / OpenClaw, with 4768 downloads so far.
How do I install Tesseract Ocr?
Run "/install tesseract-ocr" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Tesseract Ocr free?
Yes, Tesseract Ocr is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Tesseract Ocr support?
Tesseract Ocr is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Tesseract Ocr?
It is built and maintained by WhaleFall (@whalefell); the current version is v1.0.0.
More Skills