Attackers can abuse a Claude document-processing flaw to run malicious code on Linux
AI SECURITYAnthropicredteam/daily · 1 source
- Severity
- High
- Sources
- 1
What happened
A weakness in a document-handling tool used by Claude, an AI assistant made by Anthropic, can be abused by attackers. They can create a temporary file that the assistant reads and runs on a user's computer.
Like I’m new · Written by AI from 1 source · Wrong?
What to do
- Check Anthropic's advisories for a fix, as the article gives no patched version.
- Limit the file access and execution rights of Claude on Linux systems until a fix is confirmed.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
Dark Reading
Who and what is in it
Companies
Products