Hacking OpenAI
Article URL: https://www.hacktron.ai/blog/hacking-openai Comments URL: https://news.ycombinator.com/item?id=49749656 Points: 277 # Comments: 94
The HacktronAI team discovered two critical vulnerabilities, allowing them to compromise ChatGPT accounts and gain remote code execution and administrative access to OpenAI's Discourse environment. They reported the issue to OpenAI and Discourse, who promptly patched the vulnerability, with OpenAI rewarding a $6,500 bounty. The team also found that many widely-used applications relying on the libheif image-processing library could be vulnerable, including GitHub, Slack, Meta, and Ruby on Rails.
They provided a full timeline of the disclosure process and released a security advisory for Discourse users.
Written by urgent.news from Hacker News Best's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- Hacking OpenAI hacktron.ai
