Indirect prompt injection In Atlassian's Rovo chat
Prompt injection is not a new idea. But most of the write-ups you'll find are about chatbots being tricked directly. I have been a reading a lot about Indirect prompt injection bugs lately and started
blog.redtrib3.in5 min read
Abu Bakar Ramzan
AI Automation & DevOps | AI Agents | Bots | VPS setup
I have been working on a project to prevent prompt injections for AI agents. but this method of indirect prompt injections can and will bypass most of the security measures they have in place. Good work pointing it out, but this gets me wondering, how can we secure our agents against such attacks ?