Unverified50% confidenceFactExact time
METR (Model Evaluation and Threat Research) was founded in 2023 and was formerly known as ARC Evals.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOWASP has listed "insecure AI-generated code" as one of the key risks to focus on in 2025.64% similarVerifiedThe prompt injection security threat category was first systematically proposed by security researcher Simon Willison in 2022.63% similarUnverifiedThe study was published at the MSR 2026 conference and is the most systematic research to date on the quality of contributions made by AI programming agents.63% similarUnverifiedThe OWASP Top 10 threat list specifically targeting LLMs was officially published in 2023.61% similarUnverified2024年，普林斯顿大学和UIUC等机构的研究团队展示了通过间接提示注入污染RAG知识库的攻击路径60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/922292API
curl https://kongchang.com/api/v1/knowledge/claims/922292MCP
get_claim(id=922292)