Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl
pydantic-ai · pydantic-ai-slim
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| pydantic-ai PyPI |
|
|
| pydantic-ai-slim PyPI |
|
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 1.107.2 and 2.24.0, web_fetch_tool, the WebFetch local fallback, and remote FileUrl media downloads buffer the complete HTTP response body before enforcing content-size controls. An attacker-influenced URL can stream an arbitrarily large response that exhausts process memory and crashes the worker; affected media types include ImageUrl, DocumentUrl, VideoUrl, and AudioUrl. SSRF protections remain effective, and the impact is limited to availability. This issue is fixed in versions 1.107.2 and 2.24.0.
From the CVE record · GitHub_M
In pydantic-ai and pydantic-ai-slim, web_fetch_tool, the WebFetch local fallback, and remote FileUrl media downloads buffer complete HTTP responses before enforcing size limits. An attacker-influenced URL can return an arbitrarily large response, exhausting process memory and crashing the worker. The input does not specify authentication or user-interaction requirements; SSRF protections remain effective.
Check PyPI installations of pydantic-ai or pydantic-ai-slim at versions >=1.77.0 <1.107.2 or >=2.0.0b1 <2.24.0.