Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · Pydantic AI

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

mediumCVSS 3.1 6.5GHSA-v36g-jcw9-x7cw

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.

Published Oct 8, 2026

Affected packages

pydantic-ai

Ecosystem
PyPI
Affected
>= 1.77.0, < 1.107.7
Fixed in
1.107.7
Check
pip show pydantic-ai

pydantic-ai

Ecosystem
PyPI
Affected
>= 2.0.0b1, < 2.52.0
Fixed in
2.52.0
Check
pip show pydantic-ai

pydantic-ai-slim

Ecosystem
PyPI
Affected
>= 1.77.0, < 1.107.7
Fixed in
1.107.7
Check
pip show pydantic-ai-slim

pydantic-ai-slim

Ecosystem
PyPI
Affected
>= 2.0.0b1, < 2.52.0
Fixed in
2.52.0
Check
pip show pydantic-ai-slim

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

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.

Credited to SounLabs.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More Pydantic AI vulnerabilities

All Pydantic AI entries