SOC status:Duty analyst on shift

UK Cyber Defence
VulnerabilityAnalyzed

CVE-2026-107287

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.

MEDIUM 6.5EPSS 0.28%

Does this matter?

Lower severity and a low EPSS score (0.28%). Track it; it rarely justifies an emergency change on its own.

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.

CVSS 3.1
6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
EPSS
0.28% probability · 20th percentile
Public exploits
None in Exploit-DB
CISA KEV
Not listed
Weakness
CWE-400, CWE-407
Affected
pydantic/pydantic ai
Source
security-advisories@github.com
EPSS trend
0%3%5%9 October 2026: 0.28%27 October 2026: 0.28%9 October 202627 October 2026

EPSS moved from 0.3% on 9 October 2026 to 0.3% on 27 October 2026.

Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.