GHSA-v36g-jcw9-x7cw

Pydantic AI: Excessive resource use when local web fetching converts nested HTML

En bref

Publiée
Mise à jour
CVE
CVE-2026-107287
Alias
PYSEC-2026-4281, PYSEC-2026-4290
CVSS_V3
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H

Description

### Summary Applications using Pydantic AI's local web-fetch tool can experience excessive CPU and memory use when it converts attacker-controlled HTML. An agent must fetch the affected page; provider-native web fetching is not affected. ### Details Nested block elements cause HTML-to-Markdown conversion to reprocess accumulated text at each level and can greatly expand the intermediate output. The response-body limit bounds downloaded bytes, while the returned-content limit is applied only after conversion. On current releases, conversion runs in a worker thread but can still consume substantial resources and delay other work in the process. Older releases performed conversion on the event loop. ### Mitigation Upgrade to a patched release of `pydantic-ai` or `pydantic-ai-slim`. If you cannot upgrade yet, avoid using local web fetching for attacker-controlled HTML.

Paquets affectés

PaquetVersions
PyPI · pydantic-aiintroduced 1.77.0, fixed 1.107.7
PyPI · pydantic-aiintroduced 2.0.0b1, fixed 2.52.0
PyPI · pydantic-ai-slimintroduced 1.77.0, fixed 1.107.7
PyPI · pydantic-ai-slimintroduced 2.0.0b1, fixed 2.52.0

Références

Sources

SourceLicence
OSV.devCC-BY 4.0 — GitHub Advisory Database