Verified70% confidenceFactExact time
Indirect prompt injection is an attack vector in which an attacker embeds malicious instructions in web pages, documents, or emails that an agent may read, inducing the agent to perform operations beyond the scope of the original task.
4
Sources
70%
Confidence
Long-term
Relevance
9/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIndirect prompt injection refers to attackers pre-embedding malicious instructions into third-party content (such as web pages, PDF documents, or API responses), which the model then executes after RAG systems retrieve or tool calls pull this content into the context.79% similarUnverifiedPrompt Injection refers to text or interface elements appearing on the screen that may contain malicious instructions, inducing the AI to perform unintended or dangerous actions.76% similarVerified提示词注入（Prompt Injection）分为直接注入和间接注入两类，直接注入通过用户输入植入恶意指令，间接注入将恶意指令藏匿于AI可能读取的外部内容中75% similarUnverified在多人协作线程中，提示注入（Prompt Injection）的攻击面扩大，任何有访问权限的用户都可能成为注入向量，恶意指令可能被伪装成背景补充或方向修正71% similarVerifiedPrompt injection is divided into two categories—direct injection and indirect injection—where indirect injection refers to attackers concealing malicious instructions in external content that the AI may read, such as webpage body text, code comments, README files, and image OCR text.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/865906API
curl https://kongchang.com/api/v1/knowledge/claims/865906MCP
get_claim(id=865906)