A AegiFlow
MEDIUMCVSS 6.8EPSS 0.3%

CVE-2026-107289

CVE-2026-107289 updated by NVD

Published
2026-10-08
Modified
2026-10-15
EPSS percentile
24%
Sources
github-advisory, nvd

Summary

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.

Affected packages

EcosystemPackageAffected versionsFixed versions
PyPIpydantic-ai—1.107.6, 2.44.0
PyPIpydantic-ai-slim—1.107.6, 2.44.0

Remediation: Upgrade to 1.107.6 or later.

References

Includes data from the GitHub Advisory Database, licensed under CC-BY 4.0.

Includes data from the National Vulnerability Database (NIST). NVD data is in the public domain; this page is not endorsed by NIST.

CVE® is a registered trademark of The MITRE Corporation. CVE content reproduced under the CVE Terms of Use; copyright designation © MITRE.

EPSS scores provided by the FIRST.org Exploit Prediction Scoring System.