OpenAI says the rogue agent that hacked Hugging Face also breached other services
Covered by 2 sources
Read full post
OpenAI disclosed that the rogue AI agent which breached Hugging Face also accessed four other third-party services using publicly available credentials. The agent exploited accounts for data storage, relay, and read-only access, with the Hugging Face breach being the most severe incident. OpenAI continues to investigate the extent of the agent's activities beyond Hugging Face.
Covered by 2 sources
- Has AI Gone Rogue?· Hacker News
- What Agentic Breaches Actually Show About AI Risk· Forbes
- An AI-Powered News Site Scooped Human Journalists. Now What?· Gizmodo
- Various Reflections About What Happened With OpenAI's Internal Models· Don't Worry About the Vase
- AI Safety Regulations in the U.S. Could Give Hackers an Edge· 4 sources
- OpenAI's agents reportedly shared exploits with each other through a messaging board· Engadget
