Verified65% confidenceFactExact time
The root cause of prompt injection lies in the fact that LLM architecture encodes system prompts, user inputs, and externally retrieved content uniformly into the same continuous token sequence, making it impossible for the model to distinguish trusted instructions from untrusted data at the semantic level.
3
Sources
65%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
Unverified提示注入攻击的根源在于LLM在推理时无法从语义层面可靠区分「系统指令」与「用户数据」，两者均以自然语言形式存在于同一上下文窗口中84% similarUnverified提示词注入的核心原理在于LLM无法从根本上区分系统指令和用户输入，因为Transformer架构的注意力机制对所有输入token一视同仁，系统提示词与用户输入的token在数学上处于同一向量空间77% similarUnverifiedPrompt injection exploits not a vulnerability in the code parser, but the model's own insufficient awareness of the boundary between instructions and data76% similarUnverifiedLLMs are architecturally incapable of distinguishing trusted instructions from untrusted input, because they process system instructions and user input as the same text sequence, and a purely technical solution analogous to parameterized queries has yet to emerge.76% similarVerifiedThe root cause of Prompt Injection is that large models cannot structurally distinguish between "system instructions" and "user data," as both are presented as natural language text at input time.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/574729API
curl https://kongchang.com/api/v1/knowledge/claims/574729MCP
get_claim(id=574729)