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

Fecha de divulgación: . nday aún no tiene constancia de una corrección; eso no significa que no exista parche. Ninguna de las cuatro fuentes de PoC la recoge. No figura en el KEV de CISA.

why these tags

nday derives these tags by fixed rules from the facts below; NVD, the CNA and other sources do not assign them. Vocabulary and rules: ~/tags.

broken access control
CWE-863, stated by the CNA GitHub_M y NVD, republishing [email protected]
remote, unauthenticated
AV:N, PR:N, UI:N in CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N (CVSS 3.1) from the CNA GitHub_M
network
AV:N in CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N (CVSS 3.1) from the CNA GitHub_M
no authentication required
PR:N in CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N (CVSS 3.1) from the CNA GitHub_M
no user interaction
UI:N in CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N (CVSS 3.1) from the CNA GitHub_M
etapa
DIS
divulgación
cvss
6.5 MEDIUM v3.1

Ciclo de vida

Eje x en UTC; punto = minuto exacto, barra ancha = solo fecha, hueco = desconocida o inferida.
fecha desconocida
DISdivulgada
07-29T20:06Z
PATparcheada
sin registro aún
ANAanalizada
sin registro aún
POCPoC
sin registro aún
ITWexplotada
sin registro aún
KEVen KEV
sin registro aún

Descripción

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.

Original text of the CVE record (cvelist), shown as published.

Exploit conditions

What an attack needs, read from the CVSS vector.
Attack vector AV:N
Network: the attacker only needs to reach it over the network
Attack complexity AC:L
Low: no special conditions; the attacker can expect repeatable success
Privileges required PR:N
None: no account or authorization needed
User interaction UI:N
None: no action by anyone other than the attacker

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

CVSS 3.1 vector from the CVE record, scored by the CNA GitHub_M.

Registro de eventos

+DISdivulgación

GitHub_M publicó el registro CVE. CVSS 6.5, severidad media.

fuente cvelist · nday , importación masiva · en bruto
{
  "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"
  }
}

Report an error

report an error or omission

Something on this page wrong or missing? Tell the editors; if they accept it, this page's revision log says so publicly. Upstream data is not changed.

Debate de investigadores

1 investigador lo mencionó en los últimos 7 días

Publicaciones en X de investigadores de la lista de nday que mencionan este CVE, tal como se publicaron. nday no las verifica.

  1. 2026-11-20

    Publicación de @Snow_Wo1f del 2026-11-20. Inicia sesión para leerla.

Inicia sesión para leer 1 publicación.

iniciar sesión

Discussion

0 comments

No comments yet.