Vulnerability · Published Oct 8, 2026 · Assigned by GitHub_M

CVE-2026-107292Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` header

Medium 6.4

In plain English

A medium-severity security flaw in pydantic-ai from pydantic. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.1% (higher than 3% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)6.4Medium
Exploit odds (30 days)0.1%top 97.2% of all CVEs
Exploited in the wildNo reportsCISA SSVC: none
Attack toolingNoneno public tooling known

Official description

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 2.30.0, the Agent.to_web() and clai web development chat server does not validate the Host header, allowing a website visited by a developer to use DNS rebinding to reach a loopback-hosted agent as a same-origin service. The hostile page can read the served UI and submit chat requests that execute agent tools with the local process's privileges and credentials, causing data disclosure or unwanted side effects. Binding to localhost, Origin checks, and CSRF tokens do not prevent the same-origin DNS rebinding path. This issue is fixed in versions 1.107.5 and 2.30.0.

Affected packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIpydantic-ai1.107.5GHSA-q2xc-rrxj-58x9
PyPIpydantic-ai2.30.0GHSA-q2xc-rrxj-58x9
PyPIpydantic-ai1.107.5, 2.30.0PYSEC-2026-4279
PyPIpydantic-ai-slim1.107.5GHSA-q2xc-rrxj-58x9
PyPIpydantic-ai-slim2.30.0GHSA-q2xc-rrxj-58x9
PyPIpydantic-ai-slim1.107.5, 2.30.0PYSEC-2026-4288

Affected products (as reported)

VendorProductVersions
pydantic pydantic-ai >= 1.34.0, < 2.0.0b1>= 2.0.0b1, < 2.30.0
pydantic pydantic-ai-slim >= 1.34.0, < 2.0.0b1>= 2.0.0b1, < 2.30.0

Weakness: CWE-346, CWE-350 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:H/A:L

References