CVE-2026-107287

Pydantic AI: Excessive resource use when local web fetching converts nested HTML

State
Published
Severity
6.5 Medium
Published
Oct 8, 2026
Updated
Oct 14, 2026
Reserved
Oct 7, 2026

Read the record on cve.org

Description

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.7 and 2.52.0, the local web_fetch_tool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML containing deeply nested block elements. Conversion repeatedly reprocesses accumulated text and can greatly expand intermediate output before the returned-content limit is applied, allowing a model-directed fetch to delay other work in the process. Provider-native web fetching is not affected. This issue is fixed in versions 1.107.7 and 2.52.0.

Scores

CVSSScoreVectorSource
3.16.5 MediumCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:HGitHub_M

Weaknesses

  • CWE-400 Uncontrolled Resource Consumption
  • CWE-407 Inefficient Algorithmic Complexity

Affected Products

ProductVersions
pydantic-aipydantic
  • >= 1.77.0, < 1.107.7Affected
  • >= 2.0.0b1, < 2.52.0Affected
pydantic-ai-slimpydantic
  • >= 1.77.0, < 1.107.7Affected
  • >= 2.0.0b1, < 2.52.0Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.