Unverified50% confidenceFactExact time
OWASP has listed prompt injection as the top security risk for large language model applications (number one in the LLM Top 10).
1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPrompt Injection is one of the most closely watched attack surfaces in the current large language model security field.71% similarUnverified提示注入（Prompt Injection）的核心原理在于大语言模型无法可靠地区分用户的真实指令和内容中夹带的恶意指令67% similarUnverifiedAnthropic had previously focused primarily on safety and alignment research for large language models.64% similarUnverified高风险操作应要求人工审批，并将所有自然语言输入视为不可信，以防范智能体目标劫持64% similarUnverifiedUnlike traditional software security vulnerabilities, the boundaries of language model jailbreaks are inherently fuzzy, and the same output may be judged as safe or dangerous depending on the context.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/955946API
curl https://kongchang.com/api/v1/knowledge/claims/955946MCP
get_claim(id=955946)