Verified65% confidenceFactExact time
OWASP 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.
3
Sources
65%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
AI Coding Tool Security Governance: How Policy Enforcement Guardrails Ensure Enterprise Compliance
hackernewshackernews7/9/2026
Related Claims
UnverifiedThe OWASP Top 10 threat list specifically targeting LLMs was officially published in 2023.81% similarVerifiedOWASP has listed "insecure AI-generated code" as one of the key risks to focus on in 2025.75% similarUnverifiedThe OWASP Top 10 for LLM Applications list was updated in 2025.72% similarVerifiedThe prompt injection security threat category was first systematically proposed by security researcher Simon Willison in 2022.60% similarUnverifiedLlamaGuard 2 introduced in 2024 13 risk categories aligned with the MLCommons AI Safety Benchmark and supports holistic judgment across multi-turn conversation context.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/486341API
curl https://kongchang.com/api/v1/knowledge/claims/486341MCP
get_claim(id=486341)