Skip to content
Fencer Intel
medium 5.9

CVE-2026-133505 json

Tool result data shaped like a file is rebuilt as a file download or provider file reference when message history is reloaded

published 16d ago modified 3h ago also EUVD-2026-131095 , GHSA-4cj4-hgwf-4hc4

Unreviewed: the maintainers' own advisory

Published by the maintainers on their GitHub repository pydantic/pydantic-ai. GitHub has not reviewed it into the GitHub Advisory Database, so the affected packages and versions are the maintainers' word. Read the full advisory on GitHub.

cvss
5.9
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.6%
EPSS 0.6% chance of exploitation in 30 days, percentile 48%
public exploits
0
none known

Summary

When message history is serialized and loaded again, a tool result that contains a JSON object in the serialized shape of one of Pydantic AI's file types is rebuilt as that file. A third party who controls data a tool returns, such as a record that an MCP server or a function tool returns from an external system, can use this to make the application download a URL on its local network, or make the model provider read an s3:// object or uploaded file with the application's credentials. Applications are affected when tool results can contain third-party data, message history containing those results is serialized and loaded again (stored history, history a UI adapter holds on the server, or Temporal, DBOS or Prefect durable execution), and the model is one Pydantic AI downloads files for, one that honors force_download, or one whose provider resolves non-HTTP file URLs or uploaded files. History that a client submits through the Vercel AI or AG-UI adapter in the default mode is not affected. The issue is fixed in pydantic-ai and pydantic-ai-slim 1.107.10 and 2.66.0.

Patch / fix

  • pypi pydantic-ai 1.107.10, 2.66.0
  • pypi pydantic-ai-slim 1.107.10, 2.66.0

Is CVE-2026-133505 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-2026-133505 updated cvss 5.9

pydantic-ai: pydantic-ai-slim: pydantic-ai: Information disclosure via unsafe deserialization of tool results

  • Red Hat Exploit Intelligence exploit-intelligence/vulnerability-analysis-rhel9 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
4h ago

Exploit prediction

0.58% chance of exploitation in the next 30 days, higher than 48% of all scored CVEs (FIRST EPSS, 2026-11-20).

CVSS scores

assigned by version score vector
CNA 3.1 5.9 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N

Affected packages

ecosystem package affected fixed in
pypi pydantic-ai
>=1.50.0, <=1.107.9
>=2.0.0b1, <=2.65.0
1.107.10
2.66.0
pypi pydantic-ai-slim
>=1.50.0, <=1.107.9
>=2.0.0b1, <=2.65.0
1.107.10
2.66.0

Affected products

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

Classification

Weakness
  • CWE-843 Access of Resource Using Incompatible Type
  • CWE-918 Server-Side Request Forgery

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.

The maintainers of pydantic/pydantic-ai published their own advisory on GitHub. Reviewed sources take precedence over it.