Unverified50% confidenceFactExact time
Prompt injection attempts to override the system prompt and induce the model to perform unauthorized actions by embedding malicious instructions into external content processed by the model, and is logically analogous to SQL injection.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
Verified提示注入是一种针对大语言模型的攻击手法，攻击者通过在模型输入数据中嵌入恶意指令劫持模型的正常行为76% similarUnverifiedFunction calling adopts a separation design where "the model is responsible for understanding intent and the app is responsible for executing operations," ensuring the model cannot directly access the database.72% similarUnverified单模型输出常存在幻觉、逻辑跳跃或格式不规范问题，引入独立审查步骤可作为自动化质量保障71% similarVerifiedPrompt injection attacks fundamentally exploit the inherent flaw of large models in failing to separate instructions from data, and are divided into two categories: direct injection and indirect injection.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975433API
curl https://kongchang.com/api/v1/knowledge/claims/975433MCP
get_claim(id=975433)