A privilege escalation issue exists in the AI Agents feature where the node-execution tool lacks proper authorization checks. A user with the Project Viewer role can escalate privileges by interacting with an agent that has node tools enabled. The tool was authorized only by the `agent:execute` scope and executed nodes using project credentials without verifying if the requesting user had permission to execute those nodes or access the credentials. This allows a Project Viewer to execute arbitrary tool nodes and access unauthorized credential secrets. If command- or file-capable tool nodes, such as Execute Command or SSH, are enabled, this can lead to arbitrary command execution on the host server.