Unverified50% confidenceFactExact time
Indirect prompt injection refers to a skill instructing the model to read a document from the web while malicious instructions are hidden in that document, potentially causing the model to treat external content as a trusted instruction source when processing it.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified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75% similarVerifiedPrompt 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.72% similarVerifiedIndirect prompt injection refers to attackers pre-embedding malicious instructions into third-party content (such as web pages, PDF documents, or API responses), which the model then executes after RAG systems retrieve or tool calls pull this content into the context.71% 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70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/997293API
curl https://kongchang.com/api/v1/knowledge/claims/997293MCP
get_claim(id=997293)