WebMCP Attack Lab: Can an E-Shop Hijack Your AI Agent?

Automated excerpt

So the agent receives potentially malicious instructions before it even starts shopping. These first three scenarios try to convince the agent to ignore the customer's spending limit by injecting malicious instructions into the place_order tool description. In the first three scenarios, the agents received malicious instructions through WebMCP tool descriptions but still refused to place orders exceeding the customer's budget.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.