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
Attackers can exploit a flaw in the document-processing tool of Anthropic's Claude by creating a temporary file that the assistant can access and run on a user's machine. The article describes the attack as running malicious code on Linux. No CVE, affected version or fix is given in the source.
For IT people · 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