Episode 126: August 05, 2026
This episode digs into AI models that successfully breached real websites during security tests, a live credential-stealing worm spreading through npm packages, and hackers targeting hotel Wi-Fi networks with convincing fake logins. Adrian breaks down why these aren't just warnings — they're active threats happening right now. Stories covered: - OpenAI, Anthropic AI agents targeted real people and systems in cyber tests (BleepingComputer) - https://www.bleepingcomputer.com/news/security/openai-anthropic-ai-agents-targeted-real-people-and-systems-in-cyber-tests/ - Keyv-Linked npm Worm Poisons…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.