Unverified50% confidenceFactExact time
提示注入在Agent系统中尤为危险，因为被攻陷的Agent可能拥有发送邮件、删除文件、调用支付API等真实世界权限
1
Sources
50%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
Unverified拥有文件系统写权限、网络访问权限和命令执行权限的Agent遭受提示词注入可能引发数据泄露、系统破坏或横向渗透73% similarUnverified在具备工具调用能力的 Agentic 系统中，一次成功的提示注入可能导致数据泄露、恶意代码执行甚至供应链攻击73% similarUnverified研究人员已在多个主流Agent系统上复现提示注入攻击，包括诱导Agent泄露私人邮件或发送消息72% similarUnverified允许AI会话互相发消息带来安全风险，恶意构造的消息可能导致目标会话执行危险命令，如删除文件或泄露敏感信息71% 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.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/541071API
curl https://kongchang.com/api/v1/knowledge/claims/541071MCP
get_claim(id=541071)