OpenAI-Hugging Face attack doesn't mean agents are evil – unless you tell them to be

Attack models gonna attack

Open AI’s admission this week that its agents escaped the sandbox and autonomously hacked model repository Hugging Face has spawned more apocalyptic warnings of agents gone bad than we can count.

Thankfully, Renato Marinho, chief research officer at Morphus Labs and a SANS Technology Institute instructor, brought some sanity to the discussion.

“It is tempting to read this as ‘AI can now hack autonomously, the sky is falling,’” Marinho said in a Thursday blog. “Resist that.”

He went on to make three very pertinent points about the agentic attack. First, and probably most important: The models didn’t have guardrails – and that was intentional.

As OpenAI said in its mea culpa, GPT-5.6 Sol and "an even more capable pre-release model" were among those that attacked Hugging Face. It also noted that the LLMs’ “deployment safeguards were intentionally not enabled during this evaluation because it was aimed...

Copyright of this story solely belongs to theregister.com. To see the full text click HERE