latest
Tooling & Automation
The invisible payload in your clipboard
A paragraph copied from a LinkedIn post carried something the eye never sees: a run of Unicode tag characters encoding a prompt-injection instruction. Pasted into a frontier model, it halted the session. The visible text was clean; the clipboard was not. This is a known bug class -- invisible tag-character smuggling into LLM contex -- and what follows is a clean field observation of it on a major platform, the byte-level proof, and the mitigation. The part the bytes can't prove is marked as such and left open.
