MCP Security: Poisoning the Tools Your AI Trusts

0Sign in to vote or save

This site does not allow itself to be embedded. You can still read it on the original site — the toolbar below keeps your place in the directory.

Tool poisoning via description fields, rug pull attacks, cross-server shadowing, RCE in MCP client tooling, and DVMCP practice lab

Comments

Nothing yet. Say the first thing.