Some LLM routers are injecting malicious tool calls(twitter.com)

7 ポイント投稿者 kotobuki3 か月前2 コメント

Some LLM routers are injecting malicious tool calls

https://twitter.com/fried_rice/status/2042423713019412941

4 コメント

This feels different from prompt injection.

If the router modifies tool calls after the model already produced output, then the model isn't the failure point anymore — the transport layer is.

Is there any mechanism today that guarantees integrity between model output and what the client actually executes? Or are we relying entirely on trust in the routing layer?

codeboy063 か月前

trackoor0013 か月前

https://arxiv.org/abs/2604.08407

stratoatlas3 か月前