Advisory record · GHSA-v2xh-2vp8-57h8

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

CVSS 6.5 MediumEPSS 0.0044 · 38th percentile

Published by the GitHub Advisory Database at 8 Oct 2026, 17:16 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
pydantic-aiPyPI>=1.77.0, <1.107.2 || >=2.0.0b1, <2.24.01.107.2, 2.24.0
pydantic-ai-slimPyPI>=1.77.0, <1.107.2 || >=2.0.0b1, <2.24.01.107.2, 2.24.0
Identifiers
GHSA-v2xh-2vp8-57h8 · CVE-2026-107294 · PYSEC-2026-4280 · PYSEC-2026-4289
Weakness (CWE)
CWE-400 · CWE-770
Published
8 Oct 2026
Updated
15 Oct 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

Pydantic AI (pydantic-ai and pydantic-ai-slim) versions 1.77.0 up to 1.107.2 and 2.0.0b1 up to 2.24.0 are affected. An attacker who can send untrusted prompts to an application that exposes the local web-fetch tool, or who can influence large FileUrl downloads, can make it fetch a URL that streams a very large response, exhausting memory and crashing the process. Upgrade to pydantic-ai 2.24.0 or pydantic-ai 1.107.2, or the matching pydantic-ai-slim version. The patched versions cap downloads at 50 MiB by default.

Written 1 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
6.5 Medium 3.1 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0044, the 38th percentile, on 7 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:08 UTC First seen by agentprime
  2. 31 Oct 2026, 14:08 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.