# AI Red-Team and Evaluation Test Plan

- **Type**: Template (Assessment)
- **Page**: https://aipolicytracker.org/templates/ai-red-team-test-plan
- **Formats**: XLSX and DOCX
- **Current version**: v4, built 2026-11-12

A test plan and case log for adversarial and evaluation testing: accuracy, robustness, prompt injection, bias, harmful content, privacy leakage and misuse, with severity and retest tracking.

## What is inside

- Test cases sheet with area, scenario, expected and observed behaviour, outcome and severity
- Plan document: scope, independence, method, exit criteria
- Testing duties sheet: safety-testing and robustness duties on record

## Laws and frameworks it is built from

- EU AI Act (European Union), Pending review · source-linked, checked 26 Sep 2026: https://aipolicytracker.org/policies/eu-ai-act
- NIST AI RMF (United States), Verified against the official source 26 Sep 2026: https://aipolicytracker.org/policies/us-nist-ai-rmf

## Recorded duties it covers

- Large frontier developers must publish a frontier AI framework (California SB 53): https://aipolicytracker.org/obligations/us-california-sb-53-frontier-ai-framework
- Large frontier developers must send periodic summaries of catastrophic-risk assessments to the state (California SB 53): https://aipolicytracker.org/obligations/us-california-sb-53-catastrophic-risk-assessment-summaries
- Achieve appropriate accuracy, robustness and cybersecurity (EU AI Act): https://aipolicytracker.org/obligations/eu-ai-act-accuracy-robustness-cybersecurity
- Manage systemic risk for high-impact general-purpose models (EU AI Act): https://aipolicytracker.org/obligations/eu-ai-act-gpai-systemic-risk
- Providers of systemic-risk GPAI models must secure the model and its infrastructure (EU AI Act): https://aipolicytracker.org/obligations/eu-ai-act-art-55-systemic-risk-cybersecurity
- Employers and employment agencies must obtain an independent bias audit before using an automated employment decision tool (NYC Local Law 144 (automated employment decision tools)): https://aipolicytracker.org/obligations/us-new-york-city-local-law-144-bias-audit
- Operators of AI above the compute threshold must run lifecycle risk management and report safety results (AI Basic Act): https://aipolicytracker.org/obligations/south-korea-ai-basic-act-art-32-safety-measures-for-high-performance-ai
- Measure and test trustworthiness characteristics (Measure) (NIST AI RMF): https://aipolicytracker.org/obligations/us-nist-ai-rmf-measure

## Latest changes

Dataset 1e8ea28a8a93 → ef1018b7a6a2.

- **Retrieved**: 2026-11-22
- **Licence**: https://creativecommons.org/licenses/by/4.0/

> Built from structured summaries of official texts. Not legal advice. A record whose review status is not "verified" has not been confirmed against its official source by a named reviewer; open the official source before relying on any date or duty. How records are verified: https://aipolicytracker.org/verification.
