Unverified50% confidenceFactExact time
Large language models cannot structurally distinguish between user instructions and instructions embedded in content, because both are part of the same token sequence from the model's perspective.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLM无法从结构层面区分指令与数据，因为两者都以自然语言形式存在于同一上下文窗口中76% similarUnverified在大语言模型底层，系统提示词、用户输入和模型输出都是同一个token序列的不同片段，依靠特殊分隔符和训练时植入的行为模式维持边界，而非硬件或操作系统级别的隔离73% 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.73% similarUnverified提示词注入分为直接注入和间接注入两种形式，因语言模型无法区分数据与指令，凡进入上下文窗口的文本都可能被执行72% similarVerifiedThe 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.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/948685API
curl https://kongchang.com/api/v1/knowledge/claims/948685MCP
get_claim(id=948685)