[ CVE-2026-107289 · Published 8 Oct 2026 ]

Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifiers

CVSS 6.8 EPSS <1%Fix available

[ Description ]Official description

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.56.0 until 1.107.6 and 2.44.0, applications that opt attacker-influenced URLs into local network access through FileUrl with force_download='allow-local' or web_fetch_tool with allow_local_urls=True can bypass the cloud-metadata blocklist by appending an IPv6 zone identifier to an IPv6 metadata address. IPv6Address equality and hashing include the zone identifier, so the blocklist comparison fails even though the network stack ignores the zone on a non-link-local destination and reaches the metadata service, potentially exposing cloud IAM credentials. The opt-in settings are disabled by default, and the issue requires an IPv6-enabled environment. This issue is fixed in versions 1.107.6 and 2.44.0.

[ Fixes ]Fixes and patches

  • pydantic-ai 1.107.6Fixed version · GitHub Advisories · pip package pydantic-ai: upgrade to 1.107.6 or later (affected >= 1.56.0, < 1.107.6)
  • pydantic-ai 2.44.0Fixed version · GitHub Advisories · pip package pydantic-ai: upgrade to 2.44.0 or later (affected >= 2.0.0b1, < 2.44.0)
  • pydantic-ai-slim 1.107.6Fixed version · GitHub Advisories · pip package pydantic-ai-slim: upgrade to 1.107.6 or later (affected >= 1.56.0, < 1.107.6)
  • pydantic-ai-slim 2.44.0Fixed version · GitHub Advisories · pip package pydantic-ai-slim: upgrade to 2.44.0 or later (affected >= 2.0.0b1, < 2.44.0)
  • Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD
  • Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD
  • Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD
  • Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD

[ Packages ]Affected open-source packages