Unverified50% confidenceCautionExact time
提示注入是针对操作型Agent的独特新型攻击向量，恶意网页可通过视觉元素或隐藏文本向Agent注入指令，如何区分真实指令与伪造指令仍是尚未完全解决的开放问题
1
Sources
50%
Confidence
Long-term
Relevance
7/18/2026
First Seen
Sources
Related Claims
UnverifiedIndirect prompt injection refers to attack instructions hidden in external web pages, documents, or API responses accessed by an agent, where the malicious instructions are activated when the agent retrieves and injects them into the context.83% similarVerifiedIn a Prompt Injection attack, an attacker can craft a special input to induce the Agent to perform unintended operations.78% similarVerifiedThe principle of indirect prompt injection is that an attacker disguises malicious instructions as normal data, delivers them to the model through a data source trusted by the agent, and induces the model to interpret the data as instructions and execute them.75% similarUnverified环境注入是Agent因具备环境交互能力而特有的新型攻击面，攻击者将恶意指令嵌入Agent读取的外部内容中触发执行74% similarUnverified提示注入攻击（Prompt Injection）指恶意第三方在Agent处理的内容中嵌入指令，劫持Agent的行为意图73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/552258API
curl https://kongchang.com/api/v1/knowledge/claims/552258MCP
get_claim(id=552258)