Prompt injection email attacks: when reading a message is the attack
A prompt injection email needs no click to exfiltrate your data. Why telling an assistant to behave is not a control, and what actually stops it.
Blog
Notes from building Harness
How Harness works, what we're learning, and what we get wrong along the way.
AI agent guardrails: when an instruction is not a safeguard
AI agent guardrails fail when they live in the prompt. What a real constraint looks like, and the one question to ask any vendor before you trust it.