- The 8 questions to ask internally about your AI tooling
- Connector scopes, and why least privilege comes first
- Whether your audit logs actually capture what your AI assistant is doing
- How to test what your assistant can access by sending a marked string through it
Webinar
Prompt Injection: Your AI Assistant Already Works for the Attacker
Key Points
The Threat Intel Season 6 premiere covered how your AI assistant can be turned against you with nothing your existing controls catch. No attachment, no link, and in the logs it reads as a legitimate user doing ordinary work. This session covers the mechanism and the controls that hold.
Related Tags
- On-Demand
- Threat Intelligence
