Unverified50% confidenceFactExact time
Indirect prompt injection specifically refers to attackers carrying out attacks through external content that the model actively retrieves, making it more dangerous.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified工具调用使攻击面从让模型说错话升级为让模型做错事，危害从信息误导上升为实质性的数据访问和系统篡改76% similarVerifiedIndirect prompt injection conceals attack instructions within external documents, web pages, or database records retrieved by the model, and is activated when a RAG system introduces them into the context74% similarUnverifiedThe introduction of RAG expands the attack surface; attackers only need to have malicious content selected during the retrieval stage to influence outputs, without needing to poison the training data, thereby lowering the threshold for information poisoning.73% similarUnverified如果LoRA权重被逆向分析，攻击者可能从中推断出训练所用的私有数据内容，即记忆提取问题72% similarUnverifiedRAG架构引入了间接提示注入攻击面：攻击者只需在RAG检索的数据源中植入恶意指令即可操纵模型72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/996153API
curl https://kongchang.com/api/v1/knowledge/claims/996153MCP
get_claim(id=996153)