TGViewer
CloudSec Wine CloudSec Wine @cloud_sec · 2.28K subscribers
Post #996 546
🔶 When AI Gets Hijacked: Exploiting Hosted Models for Dark Roleplaying

Permiso has found that some attackers are using hijacked LLM infrastructure to power highly inappropriate AI chatbot services.

https://permiso.io/blog/exploiting-hosted-models

#aws
  • 👍 3
  • ❤ 1
  • 🔥 1
Open in Telegram All posts from @cloud_sec
More from @cloud_sec
  1. Oct 2, 2026🔴 Strengthen your CI/CD pipeline with new Secure Source Manager capabilities Google Cloud…
  2. Oct 1, 2026🔶 Exploring the new AWS Sign Up experience This post will explore what this new concept d…
  3. Sep 30, 2026🤖 Hacking OpenAI Researchers chained a libheif heap buffer overflow (via Discourse/ImageM…
  4. Sep 29, 2026👩‍💻 How to secure edge AI in customer-owned environments Edge AI shifts trust responsibi…
  5. Sep 28, 2026🤖 Containers Are No Longer a Security Boundary AI-accelerated kernel vuln discovery (5,97…
  6. Sep 25, 2026🔶 Introducing Amazon EBS Volume Clones across AWS account AWS introduces Amazon EBS Volum…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →