Verified85% confidenceFactTime unknown
Prompt Injection is a security attack method targeting AI applications, analogous to SQL injection in traditional web development.
5
Sources
85%
Confidence
Long-term
Relevance
6/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPrompt 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.75% 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68% similarUnverifiedPrompt injection refers to an attacker hiding instructions in data that the model will read, inducing the model to deviate from its original task and carry out the attacker's intent; the defense focus is on architecture rather than prompt wording, including source tagging and sanitization, least privilege, prohibiting untrusted content from triggering side-effect operations, and human confirmation before high-risk actions.66% similarUnverifiedHook injection is the most common implementation method in WeChat automation tools, directly modifying the WeChat client's runtime logic through techniques such as DLL injection, API hijacking, or process memory reading and writing, to intercept and forge sent and received messages.65% similarVerifiedPrompt 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.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/37376API
curl https://kongchang.com/api/v1/knowledge/claims/37376MCP
get_claim(id=37376)