Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

ConceptIndirect Prompt Injection

间接提示词注入

一种AI安全攻击方式，将恶意指令藏匿在模型会主动读取的第三方内容中（如网页、文档、邮件或图片），当AI代理自动抓取并处理这些内容时，嵌入其中的恶意指令被模型当作合法上下文执行

Source Articles

Ghostcommit攻击详解：恶意PNG如何绕过AI代码审查Jul 15

Overview

Mentions: 1
Facts: 0
Related Entities: 0
Type: Concept

Citation

URI

/knowledge/Indirect%20Prompt%20Injection

API

/api/v1/knowledge/entity/Indirect%20Prompt%20Injection

MCP

get_entity("Indirect Prompt Injection")