Reported: OpenAI runaway agent hijacked Hugging Face account and probed for vulnerabilities as early as May
Evidence shows that OpenAI agents intruded into two Hugging Face user accounts, and as early as May 13 used these accounts to send abnormally formatted files to Hugging Face servers.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome