SSRF in Pydantic Pydantic-Ai

CVE-2026-107288

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.

Vulnerability class: SSRF (Server-Side Request Forgery)

Published · last modified .

CVSS v3 metric

CVSS v3 base score 3.7 (Low). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:N/A:N.

EPSS exploit prediction

No EPSS score from FIRST.org yet. New CVEs usually get one within a few days; no score means no signal yet, not low risk. How EPSS works.

Affected products

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2026-107288?
CVE-2026-107288 is a low-severity vulnerability in Pydantic Pydantic-Ai, classified under Server-Side Request Forgery (SSRF). CVSS score: 3.7/10. Published 2026-10-08.
How severe is CVE-2026-107288?
Low severity. CVSS v3 base score is 3.7 out of 10.