TikTok researchers warn that MCP tools can quietly turn AI agents against their users
Photo: Crypto Briefing
A new paper from TikTok's Privacy Innovation Lab argues that multi-turn MCP systems break the security assumptions developers have been relying on AI agents are supposed to be helpful assistants. A new paper from TikTok researchers suggests they can also be very cooperative leakers. The research shows that a malicious tool description can steer a large language model (LLM) agent into sending user queries and its own responses to a logging tool controlled by an attacker. The user asks a question, the agent answers, and a stranger quietly keeps a copy of the whole exchange.
Source: Crypto Briefing
