Resource exhaustion in Pydantic Pydantic-Ai
CVE-2026-107287
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.
Vulnerability class: DoS (Denial of Service)
Published .
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H.
EPSS exploit prediction
No EPSS score from FIRST.org yet. New CVEs usually get one within a few days; no score means no signal yet, not low risk. How EPSS works.
Affected products
- Pydantic Pydantic-Ai — versions >= 1.77.0, < 1.107.7, >= 2.0.0b1, < 2.52.0
- Pydantic Pydantic-Ai-Slim — versions >= 1.77.0, < 1.107.7, >= 2.0.0b1, < 2.52.0
Weakness classification (CWE)
References
- github.com/pydantic/pydantic-ai/security/advisories/GHSA-v36g-jcw9-x7cw
- github.com/pydantic/pydantic-ai/pull/8984
- github.com/pydantic/pydantic-ai/pull/8985
- github.com/pydantic/pydantic-ai/commit/2b247add4950bef61d352e7ca8aefbd20539180c
- github.com/pydantic/pydantic-ai/commit/2fd38792693da00a3ca5412aeffb436787af3545
- github.com/pydantic/pydantic-ai/releases/tag/v1.107.7
- github.com/pydantic/pydantic-ai/releases/tag/v2.52.0
Frequently asked questions
- What is CVE-2026-107287?
- CVE-2026-107287 is a medium-severity vulnerability in Pydantic Pydantic-Ai, classified under Uncontrolled Resource Consumption. CVSS score: 6.5/10. Published 2026-10-08.
- How severe is CVE-2026-107287?
- Medium severity. CVSS v3 base score is 6.5 out of 10.