Unverified50% confidenceFactExact time
提示词注入可分为直接注入和间接注入，间接注入通过被模型读取的外部文档、网页等传递指令
1
Sources
50%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
GODMODE项目深度解析：AI越狱技术与大模型安全攻防博弈
Related Claims
Verified提示词注入（Prompt Injection）分为直接注入和间接注入两类，直接注入通过用户输入植入恶意指令，间接注入将恶意指令藏匿于AI可能读取的外部内容中79% similarPartially VerifiedPrompt injection is divided into two categories—direct injection and indirect injection—where indirect injection refers to attackers concealing malicious instructions in external content that the AI may read, such as webpage body text, code comments, README files, and image OCR text.79% similarUnverified工具调用早期实现依赖ReAct等提示词技巧，模型通过文本格式输出行动指令，再由外部代码解析执行73% similarUnverified提示注入可分为直接注入和间接注入两类，间接注入更隐蔽，已在 RAG 系统、浏览器自动化代理等场景中成功实施73% similarUnverifiedAugment Code uses a Meta-Prompt engineering mechanism that inserts a dedicated prompt-rewriting model between user input and the underlying model.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/563169API
curl https://kongchang.com/api/v1/knowledge/claims/563169MCP
get_claim(id=563169)