Unverified50% confidenceFactExact time

提示注入被OWASP列为LLM应用Top 1安全风险，其核心原理是LLM无法在结构上区分系统指令与用户输入

1

Sources

50%

Confidence

Long-term

Relevance

7/14/2026

First Seen

Sources

JadePuffer全自动AI勒索攻击实战复盘：智能体武器化时代来临

Related Claims

VerifiedOWASP已将Prompt注入列为LLM应用十大安全风险之首70% similar UnverifiedGStack的CISO命令遵循OWASP TOP 10和STRIDE威胁建模标准进行安全审查68% similar VerifiedOWASP将用户枚举攻击（User Enumeration Attack）列为常见安全风险68% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/509838

API

curl https://kongchang.com/api/v1/knowledge/claims/509838

MCP

get_claim(id=509838)