Security Affairs AI-cybersecurity newsletter round 7 flags malicious Claude Code extension
AI SECURITYAccentureredteam/daily · 1 source
- Severity
- High
- Sources
- 1
What happened
Round 7 of the Security Affairs AI-cybersecurity newsletter highlights a malicious Anthropic.claude-code build (versions 2.1.312 and 2.1.313) in the Cursor VS Code Extension Marketplace. It also reports an Accenture contractor who connected an AI agent to the Pentagon's secure network before sending data to a high-risk website. The ThisBash escape, a Claude Dispatch flaw enabling browser extension RCE on the OS, and the WorkOS data security incident are also listed. Defenders should check for the named extension versions; the headlines give no CVE IDs.
For security analysts · Written by AI from 1 source · Wrong?
What to do
- Check whether Anthropic.claude-code versions 2.1.312 or 2.1.313 are installed from the Cursor VS Code Extension Marketplace.
- Review any AI agents connected to internal networks for unapproved data transfers to external sites.
Written by AI from the sources, checked against them
Full story timeline · 2 updates
Who reported · 1 outlet
Security Affairs
Who and what is in it
Government agencies