Unverified50% confidenceCautionExact time
Prompt injection or abnormal user input may allow an Agent to access data that should have been blocked or perform operations that should not have been executed, which is an architectural-layer vulnerability where permission checks are bypassed.
1
Sources
50%
Confidence
Long-term
Relevance
9/13/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIndirect prompt injection attacks plant hidden instructions within normal business data to induce Agents into executing unauthorized operations, representing a security risk at the semantic level rather than the code level.79% similarUnverified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77% similarUnverifiedBOLA漏洞的本质是系统未能验证发起请求的用户是否有权访问或操作所请求的特定对象73% similarUnverified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72% similarUnverified涉及代码执行的任务中某些异常信息（如动态代码求值报错）可能被安全系统误读为威胁信号72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/918600API
curl https://kongchang.com/api/v1/knowledge/claims/918600MCP
get_claim(id=918600)