# HarnessRisk

> HarnessRisk, published 18 August 2026, evaluates agent harness security across six lifecycle stages and 128 sandbox cases in 14 model-harness configurations, finding attack success rates from 12.6% to 80.9%.

Splits agent harness security into six lifecycle stages and tests 128 sandbox cases.

- **Category:** Safety & security
- **2026 frontier:** Attack success rate 12.6%-80.9%; utility 75.0%-97.6% across 14 model-harness configurations
- **Credibility:** Valuable because it tests the harness rather than the model: six stages (configuration, capability extension, runtime operation, state persistence, action control, incident recovery), 128 sandbox cases, three harnesses crossed with six models for 14 configurations. The spread of 12.6% to 80.9% attack success is the headline — the same model inside a different harness is a different security posture.
- **Verification:** Verified
- **Source:** [HarnessRisk (arXiv:2608.17597)](https://arxiv.org/abs/2608.17597)
- **Last updated:** 2026-10-04