You gave your AI agent access, but who is giving it orders?
// summary
AI agents can be manipulated via malicious emails, websites, or plugins to misuse legitimate permissions for commands, data access, or file deletion, prompting discussion of runtime controls.
// from the source
AI agents can be manipulated through malicious emails, websites, and plugins into executing commands, stealing data, or deleting files using their legitimate permissions. Gen Digital explains how its Agent Trust Hub helps protect agents through skill verification, secure connectivity, and runtime controls that intercept dangerous act [...]