Verified75% confidenceFactExact time
The OWASP Top 10 threat list specifically targeting LLMs was officially published in 2023.
3
Sources
75%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
硬件级AI安全：机密计算如何实现性能与防护双赢
rss7/2/2026
Related Claims
VerifiedOWASP published the first version of the LLM Top 10 security risk list in 2023, and in the 2024 updated version refined 'Excessive Agency' (LLM08) into three dimensions: too many functions, excessive permissions, and too much autonomy.81% similarUnverifiedThe OWASP Top 10 list of risks for large language model applications was first published in 2023 and updated in 2025.80% similarUnverifiedThe OWASP Top 10 for LLM Applications list was updated in 2025.74% similarUnverifiedOWASP lists prompt injection as LLM01, the highest risk for LLM-powered applications in 2026.72% similarVerifiedThe prompt injection security threat category was first systematically proposed by security researcher Simon Willison in 2022.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/229213API
curl https://kongchang.com/api/v1/knowledge/claims/229213MCP
get_claim(id=229213)