A prompt injection vulnerability in AWS Kiro enabled manipulation of the mcp.json configuration file and code execution — AWS has implemented protection measures for sensitive file paths.
Google’s new specialized model Gemini 3.5 Flash Cyber identifies security vulnerabilities in code more accurately than competing models and is currently available only to governments and select partners.
Organizations are sacrificing established security principles for databases they previously protected rigorously in their race to develop AI capabilities.
Fraunhofer is developing person-centric voice profiles to detect audio deepfakes as general detection methods can no longer keep pace with rising synthesis quality.
1Password injects login credentials directly into websites without granting Claude access to passwords — but afterward the AI operates unrestricted within the user account.
