agent security

The security question every agent PM must answer well. Anyone can send your user an email, which means anyone can put instructions in front of the model. The strong answer stops trying to make the model resist and limits what a fooled model can do.

A textbook confused-deputy attack on a powerful agent. The interviewer wants the mechanism, the full set of controls (sandbox, network, secrets, approvals), and a response plan for the disclosure.

Untrusted pages, private data and the ability to act or send are each manageable alone and dangerous together. Set a rule for combinations, then decide where a person must confirm.

One open registry was found with 341 malicious skills out of 2,857. Decide publisher identity, version pinning, metadata rules and how fast you can pull a listing.