Verified75% confidenceFactExact time
Prompt injection attacks were first publicly demonstrated by security researcher Riley Goodside in 2022 and have been listed by OWASP as the top security risk for LLM applications.
5
Sources
75%
Confidence
Long-term
Relevance
7/7/2026
First Seen
Sources
Claude Sonnet 5发布：最强Agent能力的中端AI模型
twitterclaudeai6/30/2026
Related Claims
VerifiedOWASP已将Prompt注入列为LLM应用十大安全风险之首76% similarUnverifiedThe concept of prompt injection was first systematically proposed by security researcher Simon Willison in 2022, drawing an analogy to SQL injection attacks in traditional web security.73% similarUnverified提示词注入攻击（Prompt Injection）是LLM应用当前最受关注的威胁向量之一，被斯坦福大学安全研究组列为首要安全风险73% similarVerifiedOWASP lists User Enumeration Attacks as a common security risk.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/129613API
curl https://kongchang.com/api/v1/knowledge/claims/129613MCP
get_claim(id=129613)