pydantic-ai · pydantic-ai-slim
| Product | Affected | Fixed in |
|---|---|---|
| pydantic-ai PyPI |
|
|
| pydantic-ai-slim PyPI |
|
|
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.
From the CVE record · GitHub_M
The local web_fetch_tool and WebFetch local fallback in Pydantic AI can use excessive CPU and memory when converting attacker-controlled HTML with deeply nested block elements to Markdown. If a model-directed fetch processes that HTML, conversion can delay other work in the process. Provider-native web fetching is not affected.
Check installations of the PyPI packages pydantic-ai or pydantic-ai-slim at versions >=1.77.0 and <1.107.7, or >=2.0.0b1 and <2.52.0.