All vulnerabilities
CVE-2026-107288GHSA-22h6-qm39-v87j

pydantic-ai: Pydantic AI: web_fetch_tool blocked_domains bypass via a hostname the resolver normalizes differently

pydantic pydantic-ai
CVSS
3.7Low
ExploitationNo known exploitationNot in CISA KEV, which does not prove it is unexploitedCISA KEV
Exploit odds (EPSS)0.37%Chance of exploitation activity in the next 30 days, higher than 29% of CVEs. Scored 23 Oct 2026FIRST EPSS
Fixed inNone listedNo source names a fixed version. Check the vendor advisory below
Published8 Oct 2026Updated 8 Oct 2026CVE List

What fixes it

No source in this snapshot names a fixed version. The vendor advisories under References are the place to check.

Description

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.

Text from CVE List

Affected versions 4

  • pydantic-aiaffected: >= 1.77.0, < 1.107.6CVE List
  • pydantic-aiaffected: >= 2.0.0b1, < 2.44.0CVE List
  • pydantic-ai-slimaffected: >= 1.77.0, < 1.107.6CVE List
  • pydantic-ai-slimaffected: >= 2.0.0b1, < 2.44.0CVE List

References 9