Agent security

What changes when a language model holds tools that can act on your systems.

All MCP6 Claude API2 Security1 Compliance1
01

Prompt injection in tool-using agents — a worked example New

We found a hidden instruction block on a live marketing site while reviewing it. On a page with no agent reading it, that payload does nothing. Point an agent with tools at it and it becomes an instruction.

Working on something like this?

We build Claude integrations, MCP servers and agentic workflows for startups and SMBs in the Netherlands and across the EU.

Book a free consult