Microsoft Copilot security directory

Computer Vision API

Published by Microsoft

Medium risk

Extract rich information from images to categorize and process visual data—and protect your users from unwanted content with this Azure Cognitive Service.

Security assessment

Plutonium assessed this connector for permissions, capabilities, and security-relevant behavior.

  • Reads your private information: This connector can read data the connected service holds about you - documents, messages, contact lists, source code, customer records, or saved profile details - and pass it back to the AI.
  • Sends your data to outside companies: Anything you share with this connector flows to a third-party service. That company sees, stores, and may use the data according to their own policies.

Available capabilities

This add-on exposes 22 tools or capabilities.

  • Analyze Image
  • Analyze Image (V3) (Preview)
  • Describe Image
  • Describe Image (V3) (Preview)
  • Describe Image Content
  • Describe Image Content (V3) (Preview)
  • Describe Image URL
  • Describe Image URL (V3) (Preview)
  • Detect Objects
  • Detect Objects (V3) (Preview)
  • Generate Thumbnail
  • Generate Thumbnail (V3) (Preview)
  • Get Area of Interest
  • Get Area of Interest (V3) (Preview)
  • Optical Character Recognition (OCR) to JSON
  • Optical Character Recognition (OCR) to JSON (V3) (Preview)
  • Optical Character Recognition (OCR) to Text
  • Optical Character Recognition (OCR) to Text (V3) (Preview)
  • Recognize Domain Specific Content
  • Recognize Domain Specific Content (V3) (Preview)
  • Tag Image
  • Tag Image (V3) (Preview)

The interactive security report will load automatically.