Advisory record · GHSA-fpf4-vwcp-v4hp

Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch`

CVSS 6.5 MediumEPSS 0.0051 · 43rd percentile

Published by the GitHub Advisory Database at 8 Oct 2026, 16:48 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
pydantic-aiPyPI>=1.77.0, <1.107.6 || >=2.0.0b1, <2.44.01.107.6, 2.44.0
pydantic-ai-slimPyPI>=1.77.0, <1.107.6 || >=2.0.0b1, <2.44.01.107.6, 2.44.0
Identifiers
GHSA-fpf4-vwcp-v4hp · CVE-2026-107290 · PYSEC-2026-4277 · PYSEC-2026-4286
Weakness (CWE)
CWE-407 · CWE-1333
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 versions from 1.77.0 before 1.107.6, and from 2.0.0b1 before 2.44.0, are vulnerable, as are pydantic-ai-slim versions in the same ranges. The local web_fetch tool processes server-controlled responses in ways whose running time grows quadratically, blocking the event loop for the whole process. An attacker who can steer an agent exposed to untrusted prompts to fetch a crafted page of a megabyte or two can stall other agent runs and requests for minutes. This is an availability issue only. Upgrade to pydantic-ai 1.107.6 or 2.44.0, or pydantic-ai-slim to the same fixed versions.

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 0.0051, the 43rd 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.