#devtools

4 posts

Red warning alert on a terminal or code editor screen with malicious payload visible.

Your Coding Agents Are Now a Direct RCE Vector

Straiker's STAR Labs found 36% of successful coding agent attacks achieve remote code execution on developer machines holding source code and cloud keys. MCP ecosystem unvetted.

Data center monitoring station with multiple screens and control interfaces.

Your Claude Code Governance Defaults Just Flipped

Claude Code v2.1.207 removes the opt-in flag for auto mode on Bedrock, Vertex, and Azure—teams must now actively set disableAutoMode to maintain manual control before the update lands.