LLM agents can be hijacked to waste computational resources through carefully crafted skills that appear legitimate but steer agents toward costly execution paths—a threat that bypasses traditional task-completion checks.
This paper reveals a new attack on LLM agents that manipulates how they choose and use third-party skills. By crafting deceptive skill descriptions and instructions, attackers can trick agents into taking unnecessarily expensive detours—using more tokens and time—while still completing tasks correctly.