CVE-2026-107290: pydantic ai — Exploit & Fix

Description

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.6 and 2.44.0, the local web_fetch_tool and the WebFetch local fallback process server-controlled responses with quadratic title extraction, whitespace normalization, and ordered-list numbering. An attacker-controlled page of modest size can therefore block the event loop for an extended period, stalling other agent runs and requests, while unsupported codecs or excessive HTML or JSON nesting can abort an individual run. This issue is fixed in versions 1.107.6 and 2.44.0.

Is your site exposed to CVE-2026-107290?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

6.5

MEDIUM

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS — Exploit Prediction

0.0044

Probability of exploitation

0.37%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-1333 CWE-1333

Affected Products

Vendor	Product	Versions
pydantic	pydantic_ai	1.77.0 — 1.107.6
pydantic	pydantic_ai	2.0.0 — 2.44.0

References

Advisories & Patches

Exploits

https://github.com/pydantic/pydantic-ai/commit/c3fd1cc1f15fdbf750d78e4e3ec1e8b4d6a3d920

Other References

https://github.com/pydantic/pydantic-ai/pull/84332

Frequently Asked Questions

What is CVE-2026-107290? +

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.6 and 2.44.0, the local web_fetch_tool and the WebFetch local fallback process server-controlled responses with quadratic title extraction, whitespace normalization, and ordered-list numbering. An attacker-controlled page of modest size can therefore block the event loop for an extended period, stalling other agent runs and requests, while unsupported codecs or excessive HTML or JSON nesting can abort an individual run. This issue is fixed in versions 1.107.6 and 2.44.0. It has a CVSS v3.1 base score of 6.5 (MEDIUM).

How severe is CVE-2026-107290? +

CVE-2026-107290 has a CVSS v3.1 score of 6.5 out of 10, rated MEDIUM. This is a medium-severity vulnerability that should be remediated as part of regular maintenance. The EPSS score is 0.0044, placing it in the 0th percentile for exploitation probability.

What products are affected by CVE-2026-107290? +

CVE-2026-107290 affects products from pydantic, specifically: pydantic_ai. Check the affected products table above for specific version ranges.

How do I check if I'm vulnerable to CVE-2026-107290? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2026-66074

RabbitMQ is a messaging and streaming broker. Prior to versions 3.13.15, 4.0.20, 4.1.11, 4.2.6, and 4.3.0, match_value/3 passes the user-supplied …

CVE-2026-45409

Internationalized Domain Names in Applications (IDNA) for Python provides support for Internationalized Domain Names in Applications (IDNA) and Unicode IDNA …

CVE-2025-48058

PowSyBl (Power System Blocks) is a framework to build power system oriented software. Prior to version 6.7.2, there is a …

CVE-2025-48059

PowSyBl (Power System Blocks) is a framework to build power system oriented software. In com.powsybl:powsybl-iidm-criteria versions 6.3.0 to before 6.7.2 …

CVE-2025-6998

ReDoS in strip_whitespaces() function in cps/string_helper.py in Calibre Web and Autocaliweb allows unauthenticated remote attackers to cause denial of service …

CVE-2025-54363

Microsoft Knack 0.12.0 allows Regular expression Denial of Service (ReDoS) in the knack.introspection module. extract_full_summary_from_signature employs an inefficient regular expression …

CVE-2026-107290