TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents
As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly associated with the context that produced them. Yet as results persist across caches, recovery mechanisms, and shared runtime state, this association can break, causing a re...
Yu-Tong Zhi, Jie Zhang, Xiu-Qi Lu et al.
· 0 citations