Unverified50% confidenceFactExact time
The first edition of the OWASP Top 10 for LLM Applications in 2023 listed Prompt Injection as LLM01, and the 2025 edition still places it first and subdivides it into direct injection and indirect injection.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Can AI Agents Be Socially Engineered? Understanding Prompt Injection and Tool Permission Risks
youtubeRuleArena 攻防實驗室10/22/2026
Related Entities
Related Claims
UnverifiedThe OWASP Top 10 for LLM Applications list was updated in 2025.76% similarUnverifiedOWASP lists prompt injection as LLM01, the highest risk for LLM-powered applications in 2026.75% similarUnverifiedThe OWASP Top 10 list of risks for large language model applications was first published in 2023 and updated in 2025.64% similarUnverifiedPrompt Injection was first systematically named by security researcher Riley Goodside in 2022 and can be divided into direct injection and indirect injection.64% similarVerifiedOWASP 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.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1085889API
curl https://kongchang.com/api/v1/knowledge/claims/1085889MCP
get_claim(id=1085889)