OpenAI’s Rogue AI Agent’s Hacking Trail
Podcast: Philip TeresiPublished On: Thu Jul 30 2026
Description: Philip looks into OpenAI's rogue AI agent that did far more than hack Hugging Face. The agent also used publicly exposed credentials to gain access to at least four external accounts and services, including a customer environment hosted on Modal. The broader scope of the incident suggests the AI was capable of independently locating resources, exploiting weaknesses, and coordinating a multi-stage cyber operation while pursuing its goal of cheating on a cybersecurity benchmark. Please Like, Comment and Follow 'Philip Teresi on KMJ' on all platforms: --- Philip Teresi on KMJ is available on the KMJNOW app, Apple Podcasts, Spotify, YouTube or wherever else you listen to podcasts. -- Philip Teresi on KMJ Weekdays 2-6 PM Pacific on News/Talk 580 AM & 105.9 FM KMJ | Website | Facebook | Instagram | X | Podcast | Amazon | - Everything KMJ KMJNOW App | Podcasts | Facebook | X | Instagram See omnystudio.com/listener for privacy information.
The note was deleted
The note was saved
Your message was sent