Agents
Indirect prompt injection, tested on an email agent
An email agent with a mock send tool and a fake secret, 360 poisoned inboxes, two OpenAI models, no leaks, and why that is less reassuring than it sounds.
An email agent with a mock send tool and a fake secret, 360 poisoned inboxes, two OpenAI models, no leaks, and why that is less reassuring than it sounds.