Red Team Tactics with EA’s Johann Rehberger
Crying Out Cloud
00:00
AI Security Risks in Clawed Computer Use
This chapter explores the capabilities and security concerns of Anthropic's Clawed Computer Use feature, which enables voice and text command interactions with AI. It highlights the dangers of prompt injection attacks and the need for robust safeguards to protect against potential malware risks in AI-powered automation.
Transcript
Play full episode
