arXiv
researchactive

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

View original resource

A survey mapping the agentic AI security space across threats, defenses, evaluation methods, and open challenges, synthesizing attack classes such as goal hijacking, tool misuse, memory poisoning, and inter-agent communication risks.

Tags

agentic AIriskssecurityevaluation

At a glance

Published

2025

Jurisdiction

Global

Category

Risks and challenges

Access

Public access

More in Risks and challenges

ICO tech futures: Agentic AI

UK Information Commissioner's Office • 2026

International AI Safety Report 2026

Yoshua Bengio et al., UK DSIT • 2026

Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections

Schmotz, Abdelnabi, Andriushchenko • 2025

Related resources

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

Governance frameworks • OpenAI

OWASP Top 10 for LLM Applications

Risk taxonomies • OWASP

NIST Adversarial Machine Learning Taxonomy

Risk taxonomies • NIST

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
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges | VerifyWise AI Governance Library