# CVE-2026-107290: Pydantic AI event loop blocking in web_fetch title extraction

Source: https://junglewise.ai/threats/cve-2026-107290-pydantic-ai-event-loop-blocked-by-quadratic-title-extraction-in  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-10-08. Updated: 2026-10-08  
License: CC BY 4.0 with a link back

CVE-2026-107290 · Severity: medium · CVSS 6.5 · Published 2026-10-08

Pydantic AI's web-fetch tool processes web pages to extract titles and convert them to markdown for AI agents. An attacker can provide a specially crafted malicious webpage that causes the tool to hang for minutes, blocking the entire application and preventing other agent runs or user requests from being served until processing completes.

Technologies: [Pydantic AI](https://junglewise.ai/threats/technologies/pydantic-pydantic-ai), [pydantic-ai (PyPI)](https://junglewise.ai/threats/technologies/pydantic-ai), [pydantic-ai-slim (PyPI)](https://junglewise.ai/threats/technologies/pydantic-ai-slim). Vendors: [Pydantic](https://junglewise.ai/threats/vendors/pydantic), [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2026-107290 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-107290 being exploited in the wild.

**How severe is CVE-2026-107290?** Medium severity, with a CVSS score of 6.5, published 8 October 2026.

**Which products and versions are affected?** pydantic-ai (PyPI) ECOSYSTEM:introduced=1.77.0,fixed=1.107.6,introduced=2.0.0b1,fixed=2.44.0; pydantic-ai-slim (PyPI) ECOSYSTEM:introduced=1.77.0,fixed=1.107.6,introduced=2.0.0b1,fixed=2.44.0.

**Is there a fix for CVE-2026-107290?** Yes. pydantic-ai (PyPI): upgrade to 2.44.0 or later; pydantic-ai-slim (PyPI): upgrade to 2.44.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-107290 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-107290?** Check whether you run Pydantic AI, pydantic-ai (PyPI) or pydantic-ai-slim (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- pydantic-ai (PyPI): upgrade to 2.44.0 or later

  ```sh
  pip install "pydantic-ai>=2.44.0"
  ```

- pydantic-ai-slim (PyPI): upgrade to 2.44.0 or later

  ```sh
  pip install "pydantic-ai-slim>=2.44.0"
  ```


## Technical details

The vulnerability stems from quadratic-time regex backtracking in title extraction and HTML-to-markdown conversion steps that run on the event loop, combined with quadratic decoding complexity in Python's punycode codec. An attacker-controlled server can return a megabyte-scale response with repeated malformed HTML tags or a punycode-labeled response to cause event loop stalls of minutes. The tool also fails to handle deeply nested pages or non-text codecs gracefully, aborting agent runs instead of failing safely.

## Affected products

- Pydantic Pydantic AI

## Identifiers

- CVE-2026-107290
- GHSA-fpf4-vwcp-v4hp
- PYSEC-2026-4277
- PYSEC-2026-4286

## Timeline

- 2026-10-08: disclosed
- 2026-10-08: advisory

## Related threats

- [Pydantic AI concurrency slot leak in streamed requests](https://junglewise.ai/threats/cve-2026-107286-pydantic-ai-concurrency-limited-models-can-keep-their-slot-when)
- [Pydantic AI excessive resource consumption in HTML-to-Markdown conversion](https://junglewise.ai/threats/cve-2026-107287-pydantic-ai-excessive-resource-use-when-local-web-fetching)
- [Pydantic AI web chat UI Host header validation bypass](https://junglewise.ai/threats/cve-2026-107292-pydantic-ai-web-chat-ui-agent-to-web-clai-web-the-local-chat)
- [Pydantic AI missing content-type validation in chat endpoint](https://junglewise.ai/threats/cve-2026-107295-pydantic-ai-web-chat-ui-agent-to-web-clai-web-a-website-visited)
- [Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`](https://junglewise.ai/threats/cve-2026-107293-pydantic-ai-opentelemetry-instrumentation-retry-prompt-content)