---
id: CVE-2026-25580
title: >-
  Pydantic AI is a Python agent framework for building applications and
  workflows with Generative AI
summary: >-
  Pydantic AI is a Python agent framework for building applications and
  workflows with Generative AI. From 0.0.26 to before 1.56.0, aServer-Side
  Request Forgery (SSRF) vulnerability exists in Pydantic AI's URL download
  functionality. When …
severity: high
cvss: 8.6
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N'
cwe:
  - CWE-918
  - CWE-918
vendor: pydantic
product: pydantic_ai
affected:
  - 'pydantic_ai >= 0.0.26, < 1.56.0'
patched:
  - pydantic_ai 1.56.0
published: '2026-02-06'
updated: '2026-06-30'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-25580'
references:
  - url: >-
      https://github.com/pydantic/pydantic-ai/commit/d398bc9d39aecca6530fa7486a410d5cce936301
    label: security-advisories@github.com
  - url: >-
      https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-2jrp-274c-jhv3
    label: security-advisories@github.com
  - url: 'https://access.redhat.com/security/cve/CVE-2026-25580'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2437781'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-25580.json
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
tags:
  - nvd
epss: 0.00674
epssPercentile: 0.5007
ingestedAt: '2026-07-03T18:53:52.178Z'
---

## Overview

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.0.26 to before 1.56.0, aServer-Side Request Forgery (SSRF) vulnerability exists in Pydantic AI's URL download functionality. When applications accept message history from untrusted sources, attackers can include malicious URLs that cause the server to make HTTP requests to internal network resources, potentially accessing internal services or cloud credentials. This vulnerability only affects applications that accept message history from external users. This vulnerability is fixed in 1.56.0.

## Affected

- `pydantic_ai >= 0.0.26, < 1.56.0`

## Remediation

Upgrade past the affected range:

- `pydantic_ai 1.56.0`