CVE-2026-107288: Pydantic AI: web_fetch_tool blocked_domains bypass via a hostname the resolver normalizes differently

Severity: low (CVSS 3.7 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.4% probability of exploitation in the next 30 days
Public exploit or detection template: none known
Published: 2026-10-08 · updated 2026-10-13
Weakness: CWE-918

Description

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.

Affected products

pydantic-ai: from 1.77.0 before 1.107.6; from 2.0.0 before 2.44.0 — fixed in 1.107.6, 2.44.0

How to fix

Upgrade to a fixed version: pydantic-ai 1.107.6, 2.44.0. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2026-107288 or the next vulnerability affects your stack