Pydantic Pydantic-AI up to 1.107.5/2.43.x Web Fetch Tool input validation

Summaryinfo

A vulnerability was found in Pydantic Pydantic-AI up to 1.107.5/2.43.x. It has been rated as problematic. Affected by this issue is some unknown functionality of the component Web Fetch Tool. This manipulation causes input validation. This vulnerability is handled as CVE-2026-107288. The attack can be initiated remotely. There is not any exploit available. Upgrading the affected component is advised.

Detailsinfo

A vulnerability has been found in Pydantic Pydantic-AI up to 1.107.5/2.43.x and classified as problematic. Affected by this vulnerability is an unknown function of the component Web Fetch Tool. The manipulation with an unknown input leads to a input validation vulnerability. The CWE definition for the vulnerability is CWE-20. The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly. As an impact it is known to affect confidentiality. The summary by CVE is:

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.6 and 2.44.0, the local web_fetch_tool and the WebFetch local fallback compare blocked_domains entries with a URL hostname before both values are normalized to the form used by getaddrinfo. An attacker-influenced model can use an equivalent IDNA spelling, non-ASCII label separator, case variation, or trailing root label that resolves to a blocked host but does not match the configured string, causing the application to fetch that host with its own privileges. allowed_domains fails closed for unmatched spellings, and private-IP and cloud-metadata protections remain effective. This issue is fixed in versions 1.107.6 and 2.44.0.

It is possible to read the advisory at github.com. This vulnerability is known as CVE-2026-107288 since 10/07/2026. The exploitation appears to be easy. The attack can be launched remotely. The exploitation doesn't need any form of authentication. The technical details are unknown and an exploit is not publicly available.

Upgrading to version 1.107.6 or 2.44.0 eliminates this vulnerability.

Be aware that VulDB is the high quality source for vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• Pydantic

Name

• Pydantic-AI

Version

• 1.107.0
• 1.107.1
• 1.107.2
• 1.107.3
• 1.107.4
• 1.107.5
• 2.0
• 2.1
• 2.2
• 2.3
• 2.4
• 2.5
• 2.6
• 2.7
• 2.8
• 2.9
• 2.10
• 2.11
• 2.12
• 2.13
• 2.14
• 2.15
• 2.16
• 2.17
• 2.18
• 2.19
• 2.20
• 2.21
• 2.22
• 2.23
• 2.24
• 2.25
• 2.26
• 2.27
• 2.28
• 2.29
• 2.30
• 2.31
• 2.32
• 2.33
• 2.34
• 2.35
• 2.36
• 2.37
• 2.38
• 2.39
• 2.40
• 2.41
• 2.42
• 2.43

Website

• Product: https://github.com/pydantic/pydantic-ai/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Be aware that VulDB is the high quality source for vulnerability data.

Discussion