Verified70% confidenceFactExact time
Indirect 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.
4
Sources
70%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
Related Claims
UnverifiedPrompt injection is a novel and unique attack vector targeting operational agents; malicious web pages can inject instructions into an agent via visual elements or hidden text, and how to distinguish real instructions from forged ones remains an open problem that has not been fully solved.83% 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79% 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.78% similarUnverifiedPrompt injection attacks refer to malicious third parties embedding instructions in content processed by an Agent to hijack the Agent's intended behavior.77% similarVerifiedPrompt injection attacks are a serious threat facing local AI Agents, as maliciously crafted content in files processed by the Agent may induce it to execute dangerous operations.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/602599API
curl https://kongchang.com/api/v1/knowledge/claims/602599MCP
get_claim(id=602599)