Revealing the details of how OpenAI agents hacked Hugging Face

In one line

When a swarm of 700 OpenAI agents hacked Hugging Face in July, they left behind a public trail of evidence.

Opening excerpt

Our investigation, based on public information, reveals a large number of previously unknown agent behaviors and exploits that were used in the attack. Agents:

The agents initially had very limited access to the internet: they could load URLs, but not interact with pages or send any data. Agents created a series of workarounds, primarily using a link-shortener site to create almost a million URLs that, when chained together, let them execute code to hack Hugging Face. These links let us piece together the details of how agents gained access and how deep the compromise was.

We’ve shared our findings with OpenAI and Hugging Face. Hugging Face confirmed that these payloads match ones found in their incident response and were aware that link shorteners were used in the attack.

Hugging Face noted that they were not aware of the list of URLs we discovered and reported to them. They stated these payloads were duplicates of ones they were aware of. These links have remained publicly available for over two months since the attack.

(Excerpted from the original; full article via the source link below.)

This story hit the Hacker News front page today (13 points / 0 comments, via swarmtraces.org). Our Tech Radar aggregates daily signals on AI engineering, backend architecture and DevOps — browse the related services and further reading below, or get in touch with our team.