Cognition 0.13.0 之前的版本存在未认证的远程代码执行漏洞。该漏洞源于其代理沙箱后端默认配置为本地执行模式,且其 REST/SSE API 未启用任何身份验证机制。攻击者可在无需凭证的情况下,通过向 POST /sessions 发送请求创建会话,再向 POST /sessions/{id}/messages 发送消息,从而触发 Deep Agents 的 ReAct 循环,经由本地 Shell 后端执行由攻击者控制的 Shell 命令,最终导致以服务器进程权限执行远程代码。
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| CognicellAI | Cognition | < 0.13.0 |
affected |
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| CognicellAI | Cognition | 0 ~ 0.13.0 | - |
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POCNo comments yet