6.4
MEDIUM CVSS 3.1
CVE-2026-107292
Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` header
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.

INFO

Published Date :

Oct. 8, 2026, 5:17 p.m.

Last Modified :

Oct. 8, 2026, 5:17 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2026-107292 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

ID Vendor Product Action
1 Pydantic pydantic_ai
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 3.1 MEDIUM MITRE-CVE
CVSS 3.1 MEDIUM [email protected]
Solution
Update Pydantic AI to a patched version to prevent DNS rebinding attacks.
  • Update Pydantic AI to version 1.107.5 or later.
  • Update Pydantic AI to version 2.30.0 or later.
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-107292 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-107292 weaknesses.

CAPEC-21: Exploitation of Trusted Identifiers Exploitation of Trusted Identifiers CAPEC-59: Session Credential Falsification through Prediction Session Credential Falsification through Prediction CAPEC-60: Reusing Session IDs (aka Session Replay) Reusing Session IDs (aka Session Replay) CAPEC-75: Manipulating Writeable Configuration Files Manipulating Writeable Configuration Files CAPEC-76: Manipulating Web Input to File System Calls Manipulating Web Input to File System Calls CAPEC-89: Pharming Pharming CAPEC-111: JSON Hijacking (aka JavaScript Hijacking) JSON Hijacking (aka JavaScript Hijacking) CAPEC-141: Cache Poisoning Cache Poisoning CAPEC-142: DNS Cache Poisoning DNS Cache Poisoning CAPEC-160: Exploit Script-Based APIs Exploit Script-Based APIs CAPEC-384: Application API Message Manipulation via Man-in-the-Middle Application API Message Manipulation via Man-in-the-Middle CAPEC-385: Transaction or Event Tampering via Application API Manipulation Transaction or Event Tampering via Application API Manipulation CAPEC-386: Application API Navigation Remapping Application API Navigation Remapping CAPEC-387: Navigation Remapping To Propagate Malicious Content Navigation Remapping To Propagate Malicious Content CAPEC-388: Application API Button Hijacking Application API Button Hijacking CAPEC-510: SaaS User Request Forgery SaaS User Request Forgery CAPEC-73: User-Controlled Filename User-Controlled Filename CAPEC-89: Pharming Pharming CAPEC-142: DNS Cache Poisoning DNS Cache Poisoning CAPEC-275: DNS Rebinding DNS Rebinding

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-107292 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-107292 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • New CVE Received by [email protected]

    Oct. 08, 2026

    Action Type Old Value New Value
    Added 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.
    Added CVSS V3.1 AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:H/A:L
    Added CWE CWE-346
    Added CWE CWE-350
    Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/107xxx/CVE-2026-107292.json">CVE-2026-107292</a>
    Added Reference https://github.com/pydantic/pydantic-ai/commit/394cc1d31656620704a703a2daed752afa5135fe
    Added Reference https://github.com/pydantic/pydantic-ai/commit/871c7aeec5dfed2138655ccbccbf15c6d763bae7
    Added Reference https://github.com/pydantic/pydantic-ai/pull/7437
    Added Reference https://github.com/pydantic/pydantic-ai/pull/7438
    Added Reference https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.5
    Added Reference https://github.com/pydantic/pydantic-ai/releases/tag/v2.30.0
    Added Reference https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-q2xc-rrxj-58x9
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.