BaselineWatch
Desk

CVE-2026-107288

3.7 low SSVC exploitation: none Analyzed

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.

Fix

Patch, vendor advisory and mitigation references on NVD 9

Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.

Change history 1

  1. First seenCVSS 3.7 · pydanticNVD modified 2026-10-13 14:35

Affected (CPE criteria) 2

  • cpe:2.3:a:pydantic:pydantic_ai:*:*:*:*:*:python:*:*
  • cpe:2.3:a:pydantic:pydantic_ai:*:-:*:*:*:python:*:*

References 9