CVE-2026-107287
6.5 MoyenneDescription
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.
Produits concernés
Scores CVSS
| Version | Score | Source | Vecteur |
|---|---|---|---|
| 3.1 | 6.5 Moyenne | security-advisories@github.com | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H |
Faiblesses (CWE)
Références
- https://github.com/pydantic/pydantic-ai/commit/2b247add4950bef61d352e7ca8aefbd20539180c Patch
- https://github.com/pydantic/pydantic-ai/commit/2fd38792693da00a3ca5412aeffb436787af3545 Patch
- https://github.com/pydantic/pydantic-ai/pull/8984 PatchVendor Advisory
- https://github.com/pydantic/pydantic-ai/pull/8985 PatchVendor Advisory
- https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.7 PatchRelease NotesVendor Advisory
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.52.0 PatchRelease NotesVendor Advisory
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-v36g-jcw9-x7cw Vendor Advisory