Glossary · Term

tool rug pull

← all terms

Definition

When an AI tool advertises one behavior in its description but actually does something different.

An attack class where an MCP-served tool's natural-language description and actual implementation diverge, exploiting LLM agents that read the description but not the source code.

Mentioned in 1 episode

  1. 057
    How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack