Moark Ocr

Perform Optical Character Recognition (OCR) to extract and recognize text from images.

Security Scan

The skill's code, instructions, and required environment variable are consistent with an OCR wrapper for Gitee AI; nothing in the package suggests it is doing unrelated or hidden actions.

Purpose & Capability

Name/description state OCR via an external Gitee AI service and the package requires a single GITEEAI_API_KEY. The bundled script calls a Gitee AI endpoint (base_url=https://ai.gitee.com/v1) and uses a PaddleOCR model — these requirements match the declared purpose.

Instruction Scope

SKILL.md instructs the agent to run the included script, extract the line starting with 'OCR_RESULT:' and present it to the user. The script only reads the provided image path and (optionally) GITEEAI_API_KEY; it encodes local files to base64 and sends them to the Gitee AI API — expected for OCR but does transmit image data to an external service. Minor formatting oddity: SKILL.md asks to present output with a camera emoji and bracketed text rather than normal markdown image syntax; this is a display choice, not a security issue.

Install Mechanism

There is no automatic installer; the SKILL.md suggests installing the well-known 'openai' Python client via pip. No downloads from unknown URLs or archive extraction are present. The included script lists 'openai' as the dependency, which is consistent with the instructions.

Credentials

Only one environment variable is required: GITEEAI_API_KEY (declared as primary). The key is directly used to authenticate to the Gitee AI endpoint. No unrelated secrets or additional environment access are requested.

Persistence & Privilege

The skill does not request permanent presence (always: false), does not modify other skill configurations, and has no special system-level privileges. Autonomous invocation is allowed (platform default) but not combined with other concerning factors.

Assessment

This package appears to do what it says: it sends the provided image (as a data URI when a local file is used) to Gitee's AI endpoint and returns OCR text. Before installing, confirm the following: (1) The GITEEAI_API_KEY you supply is for a trusted Gitee AI account and you understand its permissions and billing; (2) any images you process may be transmitted to the external service — avoid sending sensitive images unless you accept that risk; (3) you will need the 'openai' Python client installed (pip install openai); (4) review and run the included script locally if you want to inspect its behavior first. If you need the OCR to run strictly offline or without external upload, this skill is not appropriate.

OCR (Optical Character Recognition)

This skill allows users to extract and recognize text from images using an external GITEE AI API.

Usage

Ensure you have installed the required dependencies (pip install openai). Use the bundled script to perform OCR on an image.

python {baseDir}/scripts/perform_ocr.py --image /path/to/image.jpg --prompt "Users requirements" --api-key YOUR_API_KEY

Options

No additional parameters are required for this skill.

Workflow

1. Execute the perform_ocr.py script with the parameters from the user.
2. Parse the script output and find the line starting with OCR_RESULT:.
3. Extract the OCR result from that line (format: OCR_RESULT: ...).
4. Display the OCR result to the user using markdown syntax: 📷[OCR Result].

Notes

• If GITEEAI_API_KEY is none, you should remind user to provide --api-key argument
• You should not only return the OCR result but also provide a brief summary of the recognized text based on the user's prompt.
• When you add prompt, you should honestly repeat the requirements from user without any additional imaginations.
• The script prints OCR_RESULT: in the output - extract this result and display it using markdown image syntax:📷[OCR Result].
• Always look for the line starting with OCR_RESULT: in the script output.