Skip to content
Fencer Intel
medium 6.4

CVE-2026-107292 json

Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` header

published last mo. modified 25d ago also EUVD-2026-95099 , GHSA-q2xc-rrxj-58x9 , PYSEC-2026-4279 , PYSEC-2026-4288

cvss
6.4
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.1%
EPSS 0.1% chance of exploitation in 30 days, percentile 2%
public exploits
0
none known

Summary

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 2.30.0, the Agent.to_web() and clai web development chat server does not validate the Host header, allowing a website visited by a developer to use DNS rebinding to reach a loopback-hosted agent as a same-origin service. The hostile page can read the served UI and submit chat requests that execute agent tools with the local process's privileges and credentials, causing data disclosure or unwanted side effects. Binding to localhost, Origin checks, and CSRF tokens do not prevent the same-origin DNS rebinding path. This issue is fixed in versions 1.107.5 and 2.30.0.

Patch / fix

  • pypi pydantic-ai 1.107.5, 2.30.0
  • pypi pydantic-ai-slim 1.107.5, 2.30.0
  • pydantic pydantic_ai 2.0.0b1, 2.30.0
  • pydantic pydantic_ai_slim 2.0.0b1, 2.30.0

Is CVE-2026-107292 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-107292 updated cvss 6.4

pydantic-ai: pydantic-ai: Unauthorized tool execution via DNS rebinding

  • Red Hat Lightspeed Core lightspeed-core/lightspeed-stack-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/disk-image-cuda-rhel9
    affected: workaround, no fix available “Fix deferred”

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
27d ago

Exploit prediction

0.13% chance of exploitation in the next 30 days, higher than 2% of all scored CVEs (FIRST EPSS, 2026-11-09).

CVSS scores

assigned by version score vector
CNA 3.1 6.4 CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:H/A:L
GitHub 3.1 6.4 CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:H/A:L
OSV 3.1 6.4 CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:H/A:L

Affected packages

ecosystem package affected fixed in
pypi pydantic-ai
>=1.34.0, <1.107.5
>=2.0.0b1, <2.30.0
1.107.5
2.30.0
pypi pydantic-ai-slim
>=1.34.0, <1.107.5
>=2.0.0b1, <2.30.0
1.107.5
2.30.0

Affected products

  • pydantic pydantic-ai
  • pydantic pydantic-ai-slim

Classification

Weakness
  • CWE-346 Origin Validation Error
  • CWE-350 Reliance on Reverse DNS Resolution for a Security-Critical Action

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.