Paper author accuses 26 LLM routers of injecting malicious tool calls and stealing credentials
The author claims one router drained their client’s $500,000 wallet, and says their team also poisoned routers to redirect traffic to themselves.
TLDR
In an April 10, 2026 post sharing a paper, an author alleged that 26 routers for large language models were injecting malicious tool calls and stealing credentials. They said one drained their client’s $500,000 wallet. The author also said their team had poisoned routers to forward traffic to themselves and claimed they could directly take over about 400 hosts within several hours.
Combined views
—
1 Source, first seen ago
