CVE-2026-107289
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.
Weakness
CISA SSVC decision points
| Exploitation | none |
|---|---|
| Automatable | no |
| Technical impact | partial |
| Scored | 2026-10-08 |
Timeline
- 2026-10-08Published by the CNA15:20 UTC
- 2026-10-08GitHub advisory published (GHSA-vmxc-h2x2-jmf3)same day
- 2026-10-08CISA SSVC decision recordedsame day
Exploit and advisory records
GitHub advisory GHSA-vmxc-h2x2-jmf3, affected packages:
| Package | Vulnerable versions | Fixed in |
|---|---|---|
| PyPI pydantic-ai | from 1.56.0 before 1.107.6 | 1.107.6 |
| PyPI pydantic-ai | from 2.0.0b1 before 2.44.0 | 2.44.0 |
| PyPI pydantic-ai-slim | from 1.56.0 before 1.107.6 | 1.107.6 |
| PyPI pydantic-ai-slim | from 2.0.0b1 before 2.44.0 | 2.44.0 |
Affected products
Products listed as vulnerable. Upgrade to the version under "Fixed in", or a later one.
| Product | Vulnerable versions | Fixed in |
|---|---|---|
| pydantic pydantic_ai | from 1.56.0 before 1.107.6fixed in 1.107.6from 2.0.0 before 2.44.0fixed in 2.44.0 | 1.107.62.44.0 |
References
- https://github.com/pydantic/pydantic-ai/commit/02157e1b87bd45d3f2e111ce07afdf89f9fb0e5b
- https://github.com/pydantic/pydantic-ai/commit/4da70591460f51a8c4f128eaeef70a33340dbd55
- https://github.com/pydantic/pydantic-ai/pull/8401
- https://github.com/pydantic/pydantic-ai/pull/8402
- https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.6
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.44.0
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-vmxc-h2x2-jmf3
Get more CVE data from the API.
curl 'https://api.contrastcyber.com/cve_lookup/CVE-2026-107289'curl 'https://api.contrastcyber.com/cve_risk_score/CVE-2026-107289'curl 'https://api.contrastcyber.com/cve_exploit/CVE-2026-107289'curl 'https://api.contrastcyber.com/cve_products/CVE-2026-107289'
Sources
- Vulnerability data from the National Vulnerability Database (NIST) and the CVE Program. CVE records: Copyright © 1999-2026, The MITRE Corporation, used under the CVE Program Terms of Use. CVE® is a registered trademark of The MITRE Corporation.
- CWE definitions: Copyright © 2006-2026, The MITRE Corporation, used under the CWE Terms of Use. CWE is a trademark of The MITRE Corporation.
- OWASP Top 10 categories by the OWASP Foundation (CC BY 3.0).
- EPSS scores by FIRST.org EPSS, used with attribution.
- KEV catalog and SSVC decisions by CISA.
- Advisory data from the GitHub Advisory Database through OSV.dev (CC BY 4.0).
- Exploit metadata from the Exploit Database (GPL-2.0-only, metadata only).
- Nuclei template names from nuclei-templates (MIT).