CVE-2026-107288

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.

References

• https://github.com/pydantic/pydantic-ai/commit/490335f8e2322e143a79337ddca9410e0176c812
• https://github.com/pydantic/pydantic-ai/commit/a9dab92099d0ef9d5d4aa34ccac8a6f1b0e51284
• https://github.com/pydantic/pydantic-ai/commit/c1f212a084cbfa0012f2044cdb4731d214b3b983
• https://github.com/pydantic/pydantic-ai/pull/8407
• https://github.com/pydantic/pydantic-ai/pull/8409