How well do prompt injection defenses work? 1,800 trials, 4 defenses, 3 models
A prompt injection defense is a control that stops text inside a model's input from making an AI agent do something its owner did not intend. We ran 1,800 trials against a mock support agent. With no defense, 69 of 300 attack trials (23.0%) succeeded. With a prompt-level defense it was 28 of 300 (9.3%), with code checks on tools 33 of 300 (11.0%), with simulated human approval 36 of 300 (12.0%), and with a URL allowlist 48 of 300 (16.0%). No defense stopped every attack.
Our lab ran these trials on 9 November 2026. The full dataset, with every transcript and a cell-by-cell explorer, is on airedteamingservices.com . This page holds the results and the data files behind them.
On this page: Results by defense · How the lab works · Results by model · What each defense stopped · Cost of a defense · Newer models · Limits · What to do · Data
Prompt injection defense success rates
Each row is one condition.…