Our research with @cyera_io shows that humans are grossly over-permissioned. Imagine what will happen if agents inherit human permissions? https://t.co/cGdtNWTwVl
meta gave their AI support agent the ability to modify your instagram account. no identity verification. people figured this out and accounts are being taken over right now
Today's suggestion ❗️💁🏻♀️
The biggest risk in AI may not be a hacked system.
It may be an agent that pursues its goal in ways we never intended.
Uncontrolled. Tricked. Weaponized ⁉️
A fascinating read on where AI security is heading:
https://t.co/FUrzi77eqz 🔗
Credit: @osoHQ 🌟🙌🏻
Have a great week! 💃🏻
#cybersecurity #infosec #AISecurity #AIAgents #AIRisk #ArtificialIntelligence #resourcesharing #RogueAIAgentDB #learningeveryday
Meta's AI customer support agent was granted the ability to modify Instagram account details. Adding it to the Agents Gone Rogue registry: https://t.co/D2aR5pi2Go
meta gave their AI support agent the ability to modify your instagram account. no identity verification. people figured this out and accounts are being taken over right now
A new addition to our 🤖 Agents Gone Rogue registry: A critical (CVSS 10.0) vulnerability in Google's Gemini CLI let attackers achieve remote code execution through CI/CD pipelines processing untrusted PRs or issues — no privileges, no user interaction required.
Oso CEO @grahamneray joined Kyle McNulty on the Secure Ventures podcast to talk agent security... as well as meeting Representative Barney Frank as a 10-year old: https://t.co/wtzUwpqiII