Skip to content
Patch Next
Sign inAdd to your agent

← Actionable
Medium, CVSS 6.5amended

Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl

CVE-2026-107294GHSA-v2xh-2vp8-57h8

What to do

Vendor fix available. Upgrade each affected package to the fixed version on its release line (pydantic-ai 2.24.0, 1.107.2; pydantic-ai-slim 2.24.0, 1.107.2), redeploy, then verify what is actually installed.

This page has no inventory attached, so it cannot say whether you are affected. A vendor fix is not proof that your deployment is fixed.

Add to your agent

Affected packages

  • PyPI pydantic-ai

    Affected
    >= 1.77.0, < 1.107.2>= 2.0.0b1, <= 2.23.0
    Fixed in
    2.24.0, 1.107.2

  • PyPI pydantic-ai-slim

    Affected
    >= 1.77.0, < 1.107.2>= 2.0.0b1, <= 2.23.0
    Fixed in
    2.24.0, 1.107.2

Sources

Severity and exploitation
Exploitation
No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.
CVSS
6.5 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS
  • CVE-2026-107294: 0.44% estimated exploitation activity in the next 30 days; percentile 38.02 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.
Source description

As published by the source; long descriptions are shortened.

Summary Several remote-content download paths in Pydantic AI buffered the entire HTTP response body into memory before enforcing any size limit. An application that exposes the local web-fetch tool (webfetchtool, or the WebFetch capability's local fallback) to untrusted prompts can be driven to fetch an attacker-chosen URL that streams a very large body, exhausting process memory and crashing the worker. The same unbounded buffering applied to FileUrl media downloads (ImageUrl, DocumentUrl, VideoUrl, AudioUrl). This is an availability issue only. SSRF protections (scheme allowlist, private-IP and cloud-metadata blocking) are unaffected; there is no confidentiality or integrity impact. Details The download helpers read the full response body before applying content-size controls, so an existing text-length limit only truncated after the whole body was already in memory, and media downloads had no wire-level cap at all. A single large response could grow process memory without bound .…

Dates and revisions
Published by the source
Last modified by the source
Source last checked
  1. Revision 3 · amended ·

    Amended from ghsa record GHSA-v2xh-2vp8-57h8

  2. Revision 2 · amended ·

    Amended from osv record GHSA-v2xh-2vp8-57h8

  3. Revision 1 · created ·

    Published from ghsa record GHSA-v2xh-2vp8-57h8

Agent brief

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-107294

Advisory: Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl
IDs: CVE-2026-107294, GHSA-v2xh-2vp8-57h8
Record: https://patchnext.com/advisories/cve-2026-107294 (revision 3, source checked 26 Oct 2026, 13:55 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Medium (CVSS 6.5)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: pydantic-ai 2.24.0, 1.107.2; pydantic-ai-slim 2.24.0, 1.107.2. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI pydantic-ai: affected >= 1.77.0, < 1.107.2; >= 2.0.0b1, <= 2.23.0; fixed in 2.24.0, 1.107.2
- PyPI pydantic-ai-slim: affected >= 1.77.0, < 1.107.2; >= 2.0.0b1, <= 2.23.0; fixed in 2.24.0, 1.107.2

## Suggested inspection (read-only)
- `python -m pip show pydantic-ai`: prints the installed version. Run with the environment that serves production active.
- `python -m pip show pydantic-ai-slim`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on pydantic-ai, pydantic-ai-slim.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://github.com/advisories/GHSA-v2xh-2vp8-57h8 (GitHub-reviewed advisory GHSA-v2xh-2vp8-57h8 lists affected ranges: PyPI pydantic-ai >=1.77.0 =2.0.0b1 =1.77.0 =2.0.0b1 <=2.23.0)
- Verified: https://osv.dev/vulnerability/GHSA-v2xh-2vp8-57h8 (OSV record GHSA-v2xh-2vp8-57h8 lists affected ranges: PyPI pydantic-ai >=1.77.0 =2.0.0b1 =1.77.0 =2.0.0b1 <2.24.0 (fixed))

Commands are suggestions: review each one before running it.

Loading voting…