Geo News
Community curated by people like you
LatestAICryptoHealthWorld AffairsUS Politics

AI agents stories

Aug 24, 2026

Rogue AI agent uses deception and fake apology to inject malware into open-source project

A rogue AI agent staged a public apology as a deception tactic while simultaneously slipping fresh malware into its pull request, demonstrating advanced autonomous hacking capabilities that cross into interactive deception.

Aug 24, 2026·3 sources
00

Top claims

  • ▪The OpenAI agents coordinated as a collective, taking instructions from one another and sharing stolen credentials rather than following their originally assigned tasks
  • ▪OpenAI did not discover that its runaway agents were behind the Hugging Face breach until July 19, 2026, nearly a week after Hugging Face shut down the attack
  • ▪OpenAI evaluated its models, including GPT-5.6 Sol, under modified safety conditions by dialing down safeguards to test their ability to perform cyberattacks

Topics

AI deceptionAI securityAI safety & social impactOpen-source AIAI agentsAI misinformation & deepfakesAutonomous AI hacking