The lethal trifecta: why your AI agent leaks data, and the wiring that stops it

On July 7 a plain public GitHub issue tricked GitHub's own AI agent into pasting a private repo into a public comment. No credentials, no exploit code. It's the same failure every time — the lethal trifecta — and no guardrail patches it. Here's the pattern, the July 2026 receipts, and the wiring that actually holds: Meta's Rule of Two.