Dataconomy
  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
Subscribe
No Result
View All Result
  • AI
  • Tech
  • Cybersecurity
  • Finance
  • DeFi & Blockchain
  • Startups
  • Gaming
Dataconomy
  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
Subscribe
No Result
View All Result
Dataconomy
No Result
View All Result

Anthropic adds file creation to Claude AI with security warnings

New tool generates spreadsheets and presentations but requires user oversight against prompt injection risks.

byKerem Gülen
September 10, 2025
in Artificial Intelligence

Anthropic has rolled out a new file creation and analysis feature for its Claude AI assistant, enabling users to generate Excel spreadsheets, PowerPoint presentations, and other documents directly within conversations.

The tool is now available in preview for Max, Team, and Enterprise subscribers, with Pro users set to gain access in the coming weeks.

What the new feature does

The feature, officially called “Upgraded file creation and analysis,” expands Claude’s existing analysis tool. It functions similarly to ChatGPT’s Code Interpreter, giving Claude the ability to work with a sandbox computing environment.

Stay Ahead of the Curve!

Don't miss out on the latest insights, trends, and analysis in the world of data, technology, and startups. Subscribe to our newsletter and get exclusive content delivered straight to your inbox.

This environment allows Claude to:

  • Download packages
  • Execute code
  • Create files such as .xlsx and .pptx
  • Analyze uploaded documents

Users can access the feature via both the web interface and the desktop app.

Security risks flagged by Anthropic

Alongside the release, Anthropic issued a security advisory warning users of potential risks. Because the feature gives Claude internet access inside the sandbox, malicious instructions could potentially be executed.

The company acknowledged:

“This feature gives Claude Internet access to create and analyze files, which may put your data at risk.”

Users are advised to closely monitor chats and stop Claude if it begins attempting actions outside expected behavior.

Vulnerability through prompt injection attacks

Anthropic’s documentation highlights the possibility of prompt injection attacks—a vulnerability first documented in 2022. These attacks occur when hidden instructions are embedded in files or websites that Claude interacts with.

A potential attack path could involve:

  1. A malicious file or website adding hidden instructions.
  2. Claude reading sensitive information from a connected knowledge source.
  3. Claude using the sandbox environment to make an external network request, leaking data.

Because AI models process all instructions in context, distinguishing between safe and malicious prompts is extremely difficult.

Mitigation and responsibility

Anthropic says it identified these risks during internal red-teaming and security testing before launch. The company’s current mitigation strategy places responsibility on the user.

The official guidance is:

  • Monitor Claude while using the feature.

  • Stop Claude immediately if it accesses or uses data unexpectedly.

This hands-on oversight requirement contrasts with the feature’s positioning as an automated productivity tool.


Featured image credit

Tags: Anthropicclaude AI

Related Posts

Samsung launches Perplexity TV app with Vision AI

Samsung launches Perplexity TV app with Vision AI

October 22, 2025
Google Skills combines courses from Cloud, DeepMind and more

Google Skills combines courses from Cloud, DeepMind and more

October 22, 2025
Yelp goes all in on AI with smart menus and virtual phone agents

Yelp goes all in on AI with smart menus and virtual phone agents

October 22, 2025
YouTube launches AI likeness detection to stop deepfake misuse

YouTube launches AI likeness detection to stop deepfake misuse

October 22, 2025
Netflix goes all in on generative AI for filmmaking

Netflix goes all in on generative AI for filmmaking

October 22, 2025
OpenAI launches ChatGPT Atlas browser for macOS

OpenAI launches ChatGPT Atlas browser for macOS

October 21, 2025

LATEST NEWS

YouTube adds a daily time limit feature for its mobile Shorts feed

Uber is now paying drivers $4,000 to buy electric cars

Samsung launches Perplexity TV app with Vision AI

Google Skills combines courses from Cloud, DeepMind and more

YouTuber builds a camera that films light at two billion FPS

NASA runs Earth-based CYZ mission to simulate life on the Moon and Mars

Dataconomy

COPYRIGHT © DATACONOMY MEDIA GMBH, ALL RIGHTS RESERVED.

  • About
  • Imprint
  • Contact
  • Legal & Privacy

Follow Us

  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
No Result
View All Result
Subscribe

This website uses cookies. By continuing to use this website you are giving consent to cookies being used. Visit our Privacy Policy.