⚡Megatron LLM Hub
←返回搜索
Twitter

spillway:面向工具调用型 Agent 的提示注入防御工具

结构约束加模型复核,可直接接进自托管 Agent 工具链。
ai_agent提示注入工具
spillway — Prompt-injection defense for tool-using agents: structure decides where agents act, a model reviews refusals. https://t.co/gXiwzGK7YO https://t.co/vKM0tYkAFD