---
id: 1298
title: "The OWASP Top 10 for LLMs 2025: How GenAI Risks Are Evolving"
source_domain: hackerone.com
source_url: "https://www.hackerone.com/blog/owasp-top-10-llms-2025-how-genai-risks-are-evolving"
published_at: "2024-12-18 21:19"
tags: ["ai-security", "prompt-injection", "llm", "owasp", "application-security", "hackerone", "top-10", "genai"]
phying_url: "https://phying.com/item/1298"
lang: en
---

# The OWASP Top 10 for LLMs 2025: How GenAI Risks Are Evolving

## Summary

OWASP's Top 10 for LLM Applications 2025 keeps prompt injection at #1 and adds system prompt leakage, vector/embedding weaknesses, and unbounded consumption; HackerOne analyzes changes and defenses.

## Intelligence Metadata

- **Sources:** hackerone.com
- **Published:** 2024-12-18 21:19
- **Original:** https://www.hackerone.com/blog/owasp-top-10-llms-2025-how-genai-risks-are-evolving
- **Phying News:** https://phying.com/item/1298