HARDE

HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control Code release for HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control. The repository contains two complementary entry-point families: domains/: the Meta-Harness baseline and the two...

HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses?

Coding agent harnesses mediate tool use and authorize actions, yet their security mechanisms and runtime effects remain incompletely characterized. We present HarnessSecurity, the first systematic empirical study and benchmark of open- and closed-source coding agent harnesses. First, we derive a...

When Context Gets Root: Privilege Escalation in LLM Harnesses

Instruction hierarchy is a model-side defense that assigns instructions different levels of privilege according to their sources. These levels constrain which content may direct model behavior. During agent execution, however, agent harnesses construct context for each model invocation. This...