Unverified50% confidenceOpinionExact time
The UK National Cyber Security Centre (NCSC) points out that language models have no equivalent isolation mechanism, and prompt injection may never be completely fixed the way SQL injection has been.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLarge language models cannot reliably distinguish the boundary between system instructions and user/external content during inference—this is a fundamental limitation of prompt injection, similar in principle to SQL injection.73% similarUnverifiedUnlike traditional SQL injection or XSS attacks, prompt injection exploits the language model's own understanding of natural language and is difficult to defend against through simple input filtering.70% similarVerified提示注入的根本原因在于大语言模型缺乏区分指令层与数据层的原生机制68% similarUnverifiedLarge language models currently have no reliable built-in defenses capable of identifying and rejecting prompt injection in all situations.67% similarVerifiedLarge language models have no natural instruction/data layering mechanism at the architectural level and cannot distinguish legitimate instructions from ordinary text in documents66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1056146API
curl https://kongchang.com/api/v1/knowledge/claims/1056146MCP
get_claim(id=1056146)