CVE-2026-25640

What it is

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 to before 1.51.0, a path traversal vulnerability in the Pydantic AI web UI allows an attacker to serve arbitrary JavaScript in the context of the application by crafting a malicious URL. In affected versions, the CDN URL is constructed using a version query parameter from the request URL. This parameter is not validated, allowing path traversal sequences that cause the server to fetch and serve attacker-controlled HTML/JavaScript from an arbitrary source on the same CDN, instead of the legitimate chat UI package. If a victim clicks the link or visits it via an iframe, attacker-controlled code executes in their browser, enabling theft of chat history and other client-side data. This vulnerability only affects applications that use Agent.to_web to serve a chat interface and clai web to serve a chat interface from the CLI. These are typically run locally (on localhost), but may also be deployed on a remote server. This vulnerability is fixed in 1.51.0.

At a glance

Exploitability

Can be exploited over the network without logging in, but needs a user to act. High risk of data exposure.

Exploit odds

0.4% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-02-06 20:16 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-07-15 02:18 UTC Last updatedMost recent change to the record

Details

Published

2026-02-06 20:16 UTC

Last modified

2026-07-15 02:18 UTC

Exploit probability

0.4% · EPSS, next 30 days

Weakness

CWE-22 · Path traversal

Record status

Modified

Affected

• Pydantic Ai < 1.51.0

Attack profile CVSS 3.1 · 7.1

Attack vector

Network

Complexity

Low

Privileges needed

None

User interaction

Required

Scope

Unchanged

Confidentiality

High

Integrity

Low

Availability

None