RedHub AI
How the gate works
How the Indirect Prompt-Injection Exposure gate works
This tool grades an AI agent's exposure to indirect prompt injection. It scores 6 weighted controls into a 0–100 number — then a gate that can only make the verdict worse.
The 6 weighted controls
When all three kill-chain controls — untrusted output, least-privilege scope, and human-in-the-loop — are open or only partial together, an injected instruction can enter, act, and go uncaught. HIGH EXPOSURE regardless of the score; close any one link and it releases.
Why: The agent scores 72 — a HARDEN band. But all three kill-chain controls are only partial at once: untrusted output can enter, an unscoped tool can act, and no human is in the loop to catch it. The chain is open end to end, so it's HIGH EXPOSURE.
The score alone reads HARDEN; the gate made it worse. The score is context; the gate is the answer — and where something is short, the fix first row names it. Grades the agent's design, not people. Not a scanner or red-team.