Viewing profile — galnagli

General-Purpose Cyber Benchmark for AI Agents and their Models

https://www.reuters.com/legal/litigation/moltbook-social-med...

Hey mmsc, first of all - the blogs are not AI Generated! Second of all, the blog did add more information "In our experimentation, exploitation of this vulnerability had high fidel…

Ian is a great writer

I see companies deploy and trust AI without really investing into security, it will be very easy in the near future to find simple, devastating bugs : )

Happy to answer questions : )

Thank you everyone, this was responsibly disclosed to DeepSeek and published after the issue was remediated, we got acknowledgment from their team today on our contribution.

Seats.aero is better

Well - they have had more bugs and will have more bugs to worry from. https://twitter.com/naglinagli/status/1639343866313601024

Web Cache Deception issue has led OpenAI's ChatGPT to suffer an account takeover vulnerability, although they don't run an official Bug Bounty program - they were quick to response…