Enterprise AI workflows can be vulnerable to misuse that exposes sensitive information without prompt injection, account compromise, or jailbreaking a large language model. This vulnerability, termed Workflow Identity Hijacking, exploits authorization gaps between external requesters and the privileged identities used by AI automation. Workflows linked to public-facing email inboxes, web forms, GitHub issues, shared documents, […]
The post Hackers Can Turn AI Workflows Into Privileged Data-Stealing Proxies Without Jailbreaking Models appeared first on Cyber Security News.