Verified65% confidenceFactExact time
Indirect 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 context
3
Sources
65%
Confidence
Long-term
Relevance
7/10/2026
First Seen
Sources
LLM Security Benchmarking: Current State, Challenges, and Practical Guide
hackernewshackernews7/6/2026
Related Claims
UnverifiedRAG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82% similarUnverified间接提示注入攻击中，攻击者只需在RAG会检索到的数据源中植入恶意指令即可操纵模型，传统WAF无法拦截81% similarUnverifiedSince malicious instructions largely originate from RAG-retrieved content and tool responses, deploying defenses only at the input entry point will miss the vast majority of the attack surface.77% similarUnverifiedIndirect prompt injection hides attack vectors in external documents or web pages read by the model, without the user's knowledge.76% similarUnverifiedIndirect prompt injection specifically refers to attackers carrying out attacks through external content that the model actively retrieves, making it more dangerous.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/461662API
curl https://kongchang.com/api/v1/knowledge/claims/461662MCP
get_claim(id=461662)