Unverified50% confidenceFactExact time
间接提示注入可将恶意指令藏入外部数据源（如网页、文档），待代理读取时自动触发攻击
1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
Unverified跨站提示注入攻击指A网站的恶意内容可能污染智能体处理B网站任务时的行为77% similarUnverified2024年已出现实际案例：通过网页内容中的隐藏指令，攻击者成功操纵具有邮件发送权限的AI助手向外部地址转发敏感内容73% similarUnverifiedDirections for defending against Prompt Injection include least-privilege design, user re-confirmation mechanisms for critical actions, and source-tagging to distinguish user instructions from webpage content.68% similarUnverifiedPrompt injection attacks could be used to induce ChatGPT connected to bank data to leak sensitive information such as users' account balances and transaction records.68% similarUnverified邮件头注入是一种服务端注入漏洞，当Web应用将用户输入未经过滤拼接进邮件头时，攻击者可通过插入CRLF进行攻击66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/527076API
curl https://kongchang.com/api/v1/knowledge/claims/527076MCP
get_claim(id=527076)