ThreatVectr
Tag

#multi-agent AI

1 story taggedmulti-agent AI.

Full-frame photoreal editorial image of a dark modern security operations centre at night, rows of monitors glowing with abstract identity graphs and network no
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