CVE-2026-107287
Pydantic AI: Excessive resource use when local web fetching converts nested HTML
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.
INFO
Published Date :
Oct. 8, 2026, 4:17 p.m.
Last Modified :
Oct. 8, 2026, 4:17 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | MEDIUM | MITRE-CVE | ||||
| CVSS 3.1 | MEDIUM | [email protected] |
Solution
- Update Pydantic AI to version 1.107.7 or later.
- Update Pydantic AI to version 2.52.0 or later.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-107287.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-107287 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-107287
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-107287 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-107287 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Oct. 08, 2026
Action Type Old Value New Value Added 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. Added CVSS V3.1 AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H Added CWE CWE-407 Added CWE CWE-400 Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/107xxx/CVE-2026-107287.json">CVE-2026-107287</a> Added Reference https://github.com/pydantic/pydantic-ai/commit/2b247add4950bef61d352e7ca8aefbd20539180c Added Reference https://github.com/pydantic/pydantic-ai/commit/2fd38792693da00a3ca5412aeffb436787af3545 Added Reference https://github.com/pydantic/pydantic-ai/pull/8984 Added Reference https://github.com/pydantic/pydantic-ai/pull/8985 Added Reference https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.7 Added Reference https://github.com/pydantic/pydantic-ai/releases/tag/v2.52.0 Added Reference https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-v36g-jcw9-x7cw