Resources

What we test, explained

Written for the people who have to decide, not only the people who build. No payloads, no jargon for its own sake.

methodology · 3 min read

Every provider, one test surface

OpenAI, Anthropic, Google, Azure, Mistral, Groq, xAI, DeepSeek, Cohere, Bedrock, self-hosted. One adapter, consistent findings.

defences · 4 min read

Least privilege for model keys

The single most effective control for AI infrastructure is also the oldest: give each key the least it needs.

attacks · 5 min read

The email an assistant reads

Copilot, Gemini and support agents read inboxes. A message can carry instructions addressed to them, invisible to the person.

fundamentals · 6 min read

What a leaked model key actually exposes

A model API key is treated like a password, but it behaves like a filesystem credential. Here is what someone holding it can reach before they ever send a prompt.