Your AI Agent Has More Authority Than Your Intern. Here Is How To Design The Limits

Description and use

<p>Out of 272,000 injection attempts against 13 frontier AI agents, 8,648 succeeded. The rate ranged from 0.5% to 8.5% depending on the model, and every model in the test proved vulnerable (Source: Large-Scale Public Red-Teaming Competition, 2026). That number stopped mattering the moment a phone vendor started rewriting its permission system because of what agents were doing with it.</p> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fgk8eub34rzn7spx

Problem

<p>Out of 272,000 injection attempts against 13 frontier AI agents, 8,648 succeeded. The rate ranged from 0.5% to 8.5% depending on the model, and every model in the test proved vulnerable (Source: Large-Scale Public Red-Teaming Competition, 2026). That number stopped mattering the moment a phone vendor started rewriting its permission system because of what agents were doing with it.</p> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fgk8eub34rzn7spx

Outcome

<p>Out of 272,000 injection attempts against 13 frontier AI agents, 8,648 succeeded. The rate ranged from 0.5% to 8.5% depending on the model, and every model in the test proved vulnerable (Source: Large-Scale Public Red-Teaming Competition, 2026). That number stopped mattering the moment a phone vendor started rewriting its permission system because of what agents were doing with it.</p> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fgk8eub34rzn7spx

Evidence

Your AI Agent Has More Authority Than Your Intern. Here Is How To Design The Limits

Source