Hackers use Claude Code to write scripts stealing FortiGate credentials
WeldPond · x · 2026-08-16
Security researchers revealed that a threat actor used Anthropic's Claude Code (Sonnet 4.6) to facilitate a network intrusion, likely for ransomware. Sonnet performed tasks such as writing an on-the-fly "LDAP capture" script, directing the victim's FortiGate device to initiate authentication and steal the service account's cleartext credentials.
More from Safety
- METR outlines three blind spots in public knowledge of AI lab internal agent risks — CFGeek · 2026-10-16
- METR researcher: scariest scenario is agents actively subverting their own safety systems — deliprao · 2026-10-16
- Cryptographer Matthew Green: Pull Critical Infrastructure Firmware Now — matthew_d_green · 2026-10-16
- Kernel-Level Agent Sandboxing With macOS Seatbelt, No Docker Needed — mostly_deterministic · 2026-10-16
- Stop giving agents raw API keys: prepaid balances and per-credential caps — Cold_Hall_5384 · 2026-10-16
- Apollo's alignment-faking experiment: model fakes compliance on 12% of responses when training is at stake — sebkrier · 2026-10-16