← Back to search
standard reviewed open access llmsec-2024-00044

OWASP Top 10 for Agentic AI Applications

OWASP Foundation

2025 — OWASP Foundation
View Resource

Abstract

Identifies the top 10 security risks specific to agentic AI applications including excessive agency, unsafe tool execution, and inadequate oversight.

Categories

threat modeling risk frameworks agent architecture

Tags

OWASPagentictop-10standard

Framework Mappings

OWASP Agentic: AGT01 OWASP Agentic: AGT02 OWASP Agentic: AGT03 OWASP Agentic: AGT04 OWASP Agentic: AGT05 OWASP Agentic: AGT06 OWASP Agentic: AGT07 OWASP Agentic: AGT08 OWASP Agentic: AGT09 OWASP Agentic: AGT10

Cite This Resource

@article{llmsec202400044,
  title = {OWASP Top 10 for Agentic AI Applications},
  author = {OWASP Foundation},
  year = {2025},
  journal = {OWASP Foundation},
  url = {https://owasp.org/www-project-top-10-for-large-language-model-applications/},
}

Metadata

Added
2026-04-14
Added by
manual
Source
manual