Selected reading
Jumping the line: How MCP servers can attack you before you ever use them
Trail of Bits demonstrates how malicious tool descriptions can influence an agent before invocation. A useful threat-modeling case study.
Trail of Bits 演示恶意工具描述如何在实际调用前影响 Agent，适合用作威胁建模案例。
Read at Trail of Bits AI and machine learning research ↗
| Publisher | Trail of Bits AI and machine learning research |
|---|---|
| Selection | Editorial selection |
| Original publication | 2025-04-21 |
| Editorial link review | 2026-10-18 |
| Link review result | ok |
| Topics | MCP security, Prompt injection, Agent security |
Use this reference
Best suited to: learn, investigate. Follow the original link for the publisher's complete context, methods, and updates.
A link review records when a reference was inspected. It is not a security certification, a reproduction of every claim, or a guarantee that the publication is current today.