nday
CVE-2026-65975 GHSA-jpr8-2v3g-wgf9

Pydantic AI AG-UI Adapter: A dangling client-submitted tool call can execute when a trailing message is dropped during `sanitize_messages`

pydantic / pydantic-ai、pydantic-ai-slim

披露于 。本站尚未获取修复依据,不能据此认为没有补丁。四个 PoC 来源都还没有收录。尚未列入 CISA KEV。

这些标签的依据

这些标签由 nday 按固定规则从下列事实自动推导,不是 NVD、编号分配方或其他来源给出的。全部标签和规则见 ~/tags。

broken access control
CWE-863(来源:编号分配方 GitHub_M、NVD(转录自 [email protected]))
远程未授权
编号分配方 GitHub_M 给出的 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N(CVSS 3.1)中的 AV:N、PR:N、UI:N
网络
编号分配方 GitHub_M 给出的 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N(CVSS 3.1)中的 AV:N
无需认证
编号分配方 GitHub_M 给出的 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N(CVSS 3.1)中的 PR:N
无需用户交互
编号分配方 GitHub_M 给出的 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N(CVSS 3.1)中的 UI:N
当前阶段
DIS
披露
CVSS
6.5 MEDIUM v3.1

生命周期

横轴 UTC;点=精确到分钟,宽条=仅日期,空心=未知或推定。
时间未知
DIS披露
07-29T20:06Z
PAT补丁
尚无记录
ANA分析
尚无记录
POCPoC
尚无记录
ITW在野
尚无记录
KEVKEV
尚无记录

摘要

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.

以上是 CVE 记录(cvelist)中的原文,未经改写。

利用条件

按 CVSS 向量说明攻击需要的条件。
攻击途径 AV:N
网络:攻击者只要能通过网络访问到目标即可
攻击复杂度 AC:L
低:不依赖特殊条件,攻击者可预期重复成功
所需权限 PR:N
无:不需要账号或授权
用户交互 UI:N
无:除攻击者外不需要任何人配合

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N

CVSS 3.1 向量,来自 CVE 记录,由 CNA GitHub_M 评定。

事件记录

+DIS披露

CVE 记录发布,编号分配方是 GitHub_M。CVSS 6.5,中危。

来源 cvelist · 本站 批量导入 · 原始记录
{
  "id": 438493,
  "type": "disclosed",
  "source": "cvelist",
  "url": "https://www.cve.org/CVERecord?id=CVE-2026-65975",
  "occurred_at": "2026-07-29T20:06:09.177Z",
  "observed_at": "2026-11-13T05:40:01.626611Z",
  "is_backfill": true,
  "dedupe_key": "",
  "detail": {
    "cvss": {
      "source": "cna",
      "vector": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N",
      "version": "3.1",
      "base_score": 6.5,
      "base_severity": "MEDIUM"
    },
    "ssvc": {
      "timestamp": "2026-07-30T13:54:02.010071Z",
      "automatable": "yes",
      "exploitation": "none",
      "technical_impact": "partial"
    },
    "state": "PUBLISHED",
    "date_published": "2026-07-29T20:06:09.177Z",
    "assigner_short_name": "GitHub_M"
  }
}

纠错

报告错误或缺失

页面有误或缺失?告诉编辑;采纳后在本页修订记录公开说明,上游数据不会被改动。

研究员讨论

近 7 天有 1 位研究员提到

研究员在 X 上提到此 CVE 的帖子,原文照录,nday 不核实。

  1. 2026-11-20

    @Snow_Wo1f 于 2026-11-20 发帖,登录后可阅读。

登录后可阅读 1 条帖子。

登录阅读

讨论

0 条评论

还没有评论。