U.S. AI Safety Institute (NIST)
researchactive

Strengthening AI Agent Hijacking Evaluations

U.S. AI Safety Institute (NIST)

View original resource

US AI Safety Institute (NIST) technical blog strengthening hijacking evaluations for agents, proposing adversarial test suites that measure resistance to indirect prompt injection. Publishes methodology and early results from frontier model evaluations.

Tags

agentic AIevaluation

At a glance

Published

2025

Jurisdiction

United States

Category

Evaluation and benchmarks

Access

Public access

More in Evaluation and benchmarks

tau-bench: A benchmark for tool-agent-user interaction

Sierra Research • 2024

SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Jimenez et al. (Princeton) • 2023

WebArena: A Realistic Web Environment for Building Autonomous Agents

Zhou et al. • 2023

Related resources

Practices for governing agentic AI systems: OpenAI's seven safety principles

Governance frameworks • OpenAI

Taxonomy of Failure Mode in Agentic AI Systems

Risk taxonomies • Microsoft

EleutherAI LM Evaluation Harness

Assessment and evaluation • EleutherAI

Build your AI governance program

VerifyWise helps you implement AI governance frameworks, track compliance, and manage risk across your AI systems.

Explore the libraryStart free trial
Strengthening AI Agent Hijacking Evaluations | VerifyWise AI Governance Library