# CVE-2026-107287: Pydantic AI: Excessive resource use when local web fetching converts nested HTML

> Attackers can cause excessive CPU and memory consumption in Pydantic AI via deeply nested HTML during local web fetching, leading to denial of service.

- **Severity:** Medium 6.5 (`CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** A user has to click or open something
- **Fix available:** Yes
- **Published:** 8 Oct 2026
- **Updated:** 14 Oct 2026
- **Also known as:** CLEANSTART-2026-HS78493, GHSA-v36g-jcw9-x7cw, PYSEC-2026-4281, PYSEC-2026-4290

## What is CVE-2026-107287?

CVE-2026-107287 is a medium-severity denial of service vulnerability in pydantic-ai, published on 8 Oct 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.

### Official 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.

Weakness: CWE-407 (Inefficient Algorithmic Complexity), CWE-400 (Uncontrolled Resource Consumption)

## Which versions are affected by CVE-2026-107287?

10 open source packages ship an affected version, including pydantic-ai and pydantic-ai-slim. It affects 1 product.


| Package | Ecosystem | Affected | Fixed in |
| --- | --- | --- | --- |
| `pydantic-ai` | PyPI | From 1.77.0 | 1.107.7, 2.52.0 |
| `pydantic-ai` | PyPI | From 1.77.0 | 1.107.7 |
| `pydantic-ai` | PyPI | From 1.77.0 | 1.107.7 |
| `pydantic-ai` | PyPI | From 2.0.0b1 | 2.52.0 |
| `pydantic-ai` | PyPI | From 2.0.0b1 | 2.52.0 |
| `pydantic-ai-slim` | PyPI | From 1.77.0 | 1.107.7, 2.52.0 |
| `pydantic-ai-slim` | PyPI | From 1.77.0 | 1.107.7 |
| `pydantic-ai-slim` | PyPI | From 1.77.0 | 1.107.7 |
| `pydantic-ai-slim` | PyPI | From 2.0.0b1 | 2.52.0 |
| `pydantic-ai-slim` | PyPI | From 2.0.0b1 | 2.52.0 |

Products: Pydantic Pydantic Ai.

## How do I fix CVE-2026-107287?

Upgrade pydantic-ai to a fixed version for your release line: 1.107.7 or 2.52.0.

## Is CVE-2026-107287 being exploited?

There is no known exploitation of CVE-2026-107287 in the wild and no public exploit code.

## Other vulnerabilities in pydantic-ai

- [CVE-2026-25580](https://insights.sbomify.com/CVE-2026-25580/): Pydantic AI Affected by Server-Side Request Forgery (SSRF) in URL Download Handling (high 8.6)
- [CVE-2026-107295](https://insights.sbomify.com/CVE-2026-107295/): Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint (high 7.6)
- [CVE-2026-107286](https://insights.sbomify.com/CVE-2026-107286/): Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early (high 7.5)
- [CVE-2026-25640](https://insights.sbomify.com/CVE-2026-25640/): Pydantic AI affected by Stored XSS via Path Traversal in Web UI CDN URL (high 7.1)
- [CVE-2026-107289](https://insights.sbomify.com/CVE-2026-107289/): Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv6 zone identifiers (medium 6.8)

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-107287 and fix it if it is affected.

What it is: CVE-2026-107287 is a medium-severity denial of service vulnerability in pydantic-ai, published on 8 Oct 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.
Exploitation: There is no known exploitation of CVE-2026-107287 in the wild and no public exploit code.

Affected packages and fixed versions:
- pydantic-ai (PyPI): affected from 1.77.0; fixed in 1.107.7, 2.52.0
- pydantic-ai (PyPI): affected from 1.77.0; fixed in 1.107.7
- pydantic-ai (PyPI): affected from 1.77.0; fixed in 1.107.7
- pydantic-ai (PyPI): affected from 2.0.0b1; fixed in 2.52.0
- pydantic-ai (PyPI): affected from 2.0.0b1; fixed in 2.52.0
- pydantic-ai-slim (PyPI): affected from 1.77.0; fixed in 1.107.7, 2.52.0
- pydantic-ai-slim (PyPI): affected from 1.77.0; fixed in 1.107.7
- pydantic-ai-slim (PyPI): affected from 1.77.0; fixed in 1.107.7
- pydantic-ai-slim (PyPI): affected from 2.0.0b1; fixed in 2.52.0
- pydantic-ai-slim (PyPI): affected from 2.0.0b1; fixed in 2.52.0

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-107287/ (Markdown: https://insights.sbomify.com/CVE-2026-107287/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-107287
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-107287
- OSV: https://osv.dev/vulnerability/CVE-2026-107287

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-107287/
Summaries are generated and may contain mistakes; the official description above is the record.