Verified90% confidenceFactTime unknown
Prompt注入（Prompt Injection）是针对大语言模型应用的安全威胁，攻击者通过在输入中嵌入恶意指令试图覆盖系统原有行为约束
14
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIndirect Prompt Injection is the most harmful variant of Prompt Injection, where an attacker plants hidden instructions on a public page to have an agent execute them.76% similarUnverifiedPrompt injection is one of the most serious security threats facing LLM applications, and its mechanism is analogous to SQL injection in traditional web security.76% similarVerifiedPrompt injection attacks induce AI agents to execute malicious operations by embedding text disguised as system instructions in code comments, documentation, web content, or even file names.75% similarUnverifiedPrompt注入攻击是当前Agent安全领域最受关注的威胁之一75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/34974API
curl https://kongchang.com/api/v1/knowledge/claims/34974MCP
get_claim(id=34974)