CyberRota Analysis
AI-GeneratedThe vulnerability affects Pydantic AI versions 1.77.0 to 1.107.6 and 2.44.0, allowing an attacker to exploit the local web_fetch_tool and WebFetch fallback mechanism by crafting URLs that bypass domain blocking due to normalization issues. This could enable unauthorized access to blocked hosts under the application's privileges, posing a risk to data integrity and confidentiality. Organizations using affected versions should prioritize upgrading to versions 1.107.6 or 2.44.0 to mitigate this risk.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.6 and 2.44.0, the local web_fetch_tool and the WebFetch local fallback compare blocked_domains entries with a URL hostname before both values are normalized to the form used by getaddrinfo. An attacker-influenced model can use an equivalent IDNA spelling, non-ASCII label separator, case variation, or trailing root label that resolves to a blocked host but does not match the configured string, causing the application to fetch that host with its own privileges. allowed_domains fails closed for unmatched spellings, and private-IP and cloud-metadata protections remain effective. This issue is fixed in versions 1.107.6 and 2.44.0.