By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Tool poisoning and rug pulls

Tool metadata such as names, descriptions, and schemas goes straight into the model's context, so a malicious MCP server can steer an agent before any tool is called. Rug pulls go a step further by changing a tool's definition or behavior after a user has approved it.

Read in this order

  1. ArticleSecurity alert: Malicious postmark-mcp npm package impersonating Postmark (Postmark)A real MCP server that quietly copied every email it sent to the attacker.
  2. ArticleInvariant Labs: MCP Security Notification: Tool Poisoning AttacksThe disclosure that named tool poisoning, with a working proof of concept.
  3. ArticleElastic Security Labs: MCP Tools: Attack Vectors and Defense Recommendations for Autonomous AgentsAttack vectors listed next to concrete defense recommendations for autonomous agents.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.