Unverified50% confidenceFactExact time
Context injection refers to the process in which, when calling the LLM, the agent concatenates specific text content into the model's input prompt, thereby influencing the model's output.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Hand-Writing Agents.md Significantly Improves AI Coding Stability
bilibiliUP进化论10/27/2026
Related Entities
Related Claims
Unverified大语言模型的执行层通过 Function Calling（工具调用）机制将 LLM 的文本输出转化为对真实系统的操作指令78% similarUnverifiedThe input an LLM receives is a single token stream; the application layer concatenates the system prompt, user messages and retrieved content into one piece of text, and there are no field markers inside the model indicating whether a given token segment is instruction or data.76% similarUnverifiedPrompt Injection refers to malicious text being embedded in content that the model will read, in an attempt to override or tamper with the original instructions.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.73% similarUnverifiedTraditional LLMs are passive text generators, whereas agents build upon this by adding a complete closed-loop capability of perception, planning, and execution73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1104694API
curl https://kongchang.com/api/v1/knowledge/claims/1104694MCP
get_claim(id=1104694)