CVE-2026-65975— pydantic-ai 授权问题漏洞
一分钟漏洞结论
影响对象
pydantic pydantic-ai
利用判断
尚无明确在野利用证据，仍需结合暴露面评估
建议动作
优先检查厂商安全公告和参考链接中的修复版本；无法立即升级时，限制受影响服务暴露并加强监测。
Pydantic pydantic-ai是Pydantic组织开源的一个用于构建生产级应用程序和工作流的生成式AI框架。 pydantic-ai 1.88.0版本至1.107.1之前版本和2.0.0b1版本至2.5.0之前版本存在授权问题漏洞，该漏洞源于UI适配器中sanitize_messages清理逻辑存在缺陷，可能导致远程客户端绕过安全检查，使非审批服务器工具以客户端提供的参数执行。
可能的 ATT&CK 技术 1 AI
T1190 · Exploit Public-Facing Application影响版本矩阵 4
| 厂商 | 产品 | 版本范围 | 状态 |
|---|---|---|---|
| pydantic | pydantic-ai | >= 1.88.0, < 1.107.1 |
affected |
>= 2.0.0b1, < 2.5.0 |
affected | ||
| pydantic | pydantic-ai-slim | >= 1.88.0, < 1.107.1 |
affected |
>= 2.0.0b1, < 2.5.0 |
affected |
获取后续新漏洞提醒
登录后订阅
一、 漏洞 CVE-2026-65975 基础信息
漏洞信息
对漏洞内容有疑问？看看神龙的深度分析是否有帮助！
查看神龙十问 ↗
尽管我们使用了先进的大模型技术，但其输出仍可能包含不准确或过时的信息。神龙努力确保数据的准确性，但请您根据实际情况进行核实和判断。
Vulnerability Title
Pydantic AI AG-UI Adapter: A dangling client-submitted tool call can execute when a trailing message is dropped during `sanitize_messages`
来源: CVE Program / CVE List V5
Vulnerability Description
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. In versions 1.88.0 up to but not including 1.107.1 and 2.0.0b1 up to but not including 2.5.0, the UI adapters (AG-UI via Agent.to_ag_ui()/AGUIAdapter, and Vercel AI via VercelAIAdapter) use sanitize_messages to strip unresolved ("dangling") client-submitted tool calls from untrusted message history before it reaches the agent, a defense-in-depth default that prevents the agent from executing tool calls the model never emitted. However, the strip anchored to a message index computed before sanitization ran, so when a trailing client message sanitized to empty and was dropped (for example a client system message under the default manage_system_prompt='server'), a preceding assistant response carrying an unresolved tool call became the new tail and was dispatched without inspection. As a result, a remote client could cause a registered, non-approval server tool to run with client-supplied arguments rather than arguments the model produced. The impact is bounded by what the affected tools do and is most significant for applications that gate tool execution in a model-request hook (before_model_request / after_model_request), since a forged call skips the model turn and bypasses that guardrail; approval-gated tools (requires_approval=True) are not auto-executed by this path. This issue has been fixed in versions 1.107.1 and 2.5.0.
来源: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
来源: CVE Program / CVE List V5
Vulnerability Type
授权机制不正确
来源: CVE Program / CVE List V5
Vulnerability Title
pydantic-ai 授权问题漏洞
来源: 中国国家信息安全漏洞库 CNNVD
Vulnerability Description
Pydantic pydantic-ai是Pydantic组织开源的一个用于构建生产级应用程序和工作流的生成式AI框架。 pydantic-ai 1.88.0版本至1.107.1之前版本和2.0.0b1版本至2.5.0之前版本存在授权问题漏洞，该漏洞源于UI适配器中sanitize_messages清理逻辑存在缺陷，可能导致远程客户端绕过安全检查，使非审批服务器工具以客户端提供的参数执行。
来源: 中国国家信息安全漏洞库 CNNVD
CVSS Information
N/A
来源: 中国国家信息安全漏洞库 CNNVD
Vulnerability Type
N/A
来源: 中国国家信息安全漏洞库 CNNVD
受影响产品
| 厂商 | 产品 | 影响版本 | CPE | 订阅 |
|---|---|---|---|---|
| pydantic | pydantic-ai | >= 1.88.0, < 1.107.1 | - |
|
| pydantic | pydantic-ai-slim | >= 1.88.0, < 1.107.1 | - |
|
二、漏洞 CVE-2026-65975 的公开POC
| # | POC 描述 | 源链接 | 神龙链接 |
|---|
AI 生成 POC
高级
未找到公开 POC。
登录以生成 AI POC三、漏洞 CVE-2026-65975 的情报信息
请登录查看更多情报信息。
CVE-2026-65975 厂商安全公告 (1)
同批安全公告 · pydantic · 2026-07-29 · 共 3 条
| CVE-2026-46678 | 6.8 MEDIUM | pydantic-ai 服务端请求伪造漏洞 |
| CVE-2026-54249 | 6.8 MEDIUM | pydantic-ai 服务端请求伪造漏洞 |
IV. Related Vulnerabilities
Same product: pydantic-ai
Same vendor: pydantic
V. Comments for CVE-2026-65975
暂无评论