Verified65% confidenceCautionExact time
Prompt 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.
3
Sources
65%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Verified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77% similarVerifiedIndirect 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.76% similarUnverifiedA prompt injection attack refers to a situation where maliciously crafted web pages in an agent's environment inject new instructions, causing the agent's behavior to deviate from the designer's intentions.73% similarVerifiedIndirect 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.72% similarUnverifiedPrompt injection induces agents to perform unauthorized operations by embedding text disguised as instructions within content processed by the agent, operating on a principle similar to SQL injection.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/908675API
curl https://kongchang.com/api/v1/knowledge/claims/908675MCP
get_claim(id=908675)