1
Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control
AI代理工具调用存在致命漏洞，MCP代理强制访问控制补齐安全短板，值得关注。
arXiv:2605.18414v2 Announce Type: replace-cross Abstract: Large language models increasingly operate as autonomous agents that select and invoke tools…