ThreatVectr
Tag

#multi-agent AI

2 stories taggedmulti-agent AI.

A computer screen showing multiple AI agent windows running coordinated tasks—one scanning networks, one attempting credential theft, one accessing systems—repr
AI Security

Criminals Are Wiring Up AI 'Agents' to Steal Passwords at Scale, Google Warns

Google's threat researchers say attackers have moved past chatbot prompts and are building small squads of AI programs that plan, scan and steal on their own.

4 min read
A developer's workstation showing Google's AI coding assistant interface with code suggestions appearing, while background elements show how malicious prompts c
AI Security

Google's AI Coding Assistants Could Be Tricked Into Leaking Secrets and Sabotaging Code

A newly exposed attack technique shows how a low-level AI agent inside Google's development toolkit can be manipulated into poisoning a higher-trust agent, giving attackers a path to steal credentials and tamper with software projects.

3 min read
© 2026 Threat Vectr