Unverified50% confidenceFactExact time
Indirect prompt injection (IPI) is hiding malicious instructions in external content that the Agent will autonomously read, such as hidden text on a webpage, the body of an email, PDF annotations or image alt attributes.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
Verified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72% 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66% similarUnverifiedIntroducing a human approval step for sensitive agent operations—such as sending emails, deleting files, or calling external APIs—can intercept attacks before they cause damage.62% similarUnverifiedRetrieved external content (emails, attachments, documents) should be treated as untrusted input, and adversarial documents should be included in evaluation sets.60% similarUnverifiedGuardrail mechanisms such as content filtering, domain whitelisting, and secondary confirmation of dangerous operations should be added to AI agent browsing and actions.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023915API
curl https://kongchang.com/api/v1/knowledge/claims/1023915MCP
get_claim(id=1023915)