Unverified50% confidenceFactExact time
Echo-like attacks are a typical weakness of RAG architectures: attackers disguise malicious instructions as retrieved result fragments, and the model mistakes them for legitimate instructions and performs operations such as deletion and data exfiltration.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
Unverified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79% 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% 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75% 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 context73% similarUnverifiedCommon RAG mistakes include improper chunking strategies, mismatch between the embedding model and queries, and lack of reranking on retrieved results.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1024486API
curl https://kongchang.com/api/v1/knowledge/claims/1024486MCP
get_claim(id=1024486)