# How to run a clean benchmark with network limits against rubric leaks with harness2

Repo: [google-research/harness2](https://github.com/google-research/harness2) | Difficulty: Advanced | Time: 1 hour | Basis: Seen in the wild

Lock down network access before evaluating so an agent cannot look up public benchmark answers.

**Who it is for:** Researcher reporting harness-improvement numbers who must show the agent could not read public rubrics

**The problem:** Executors have open web access and public rubrics may exist online, so scores can be inflated by looking up answers.

**The outcome:** A benchmark run done under network restrictions, giving numbers you can defend as not contaminated by leaked grading criteria.

## Steps

1. Read the web access section of docs/EXPERIMENTS.md and apply its network restrictions.
2. Preview task selection with no model calls by adding --dry-run to your harness2 command.
3. Run the real refinement: harness2 --bench lab --k 1 --mode parallel --only-domains antitrust-competition --max-tasks 1
4. Judge: harness2-judge --bench lab --k 1 --mode parallel
5. Report: harness2-report --bench lab --k 1 --mode parallel

## Prompt to paste into your agent

```text
Before running any model-backed benchmark in google-research/harness2, read the web access section in docs/EXPERIMENTS.md and tell me what network restrictions to configure for <benchmark>. Then run a --dry-run preview and verify task selection looks right.
```

## Caveat

Authorized use only: run this only inside infrastructure you control, since the README states executors have unrestricted network access and Codex runs with its sandbox disabled, and public rubrics may be online.

## Seen in the wild

- X (Oct 2026): https://x.com/i/web/status/2112265188091265326
- X (Oct 2026): https://x.com/i/web/status/2112254069184344121

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/google-research-harness2/benchmark-agent-harness-without-answer-leaks/