Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 2.30.0, the Agent.to_web() and clai web development chat server does not validate the Host header, allowing a website visited by a developer to use DNS rebinding to reach a loopback-hosted agent as a same-origin service. The hostile page can read the served UI and submit chat requests that execute agent tools with the local process's privileges and credentials, causing data disclosure or unwanted side effects.
Binding to localhost, Origin checks, and CSRF tokens do not prevent the same-origin DNS rebinding path. This issue is fixed in versions 1.107.5 and 2.30.0.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
High
Difficult to exploit
Privileges Required
None
No privileges needed
User Interaction
Required
User action required
Impact Assessment
Confidentiality
Low
Partial data leak
Integrity
High
Complete data modification
Availability
Low
Partial disruption
CVSS Vector v3.1
Weakness Type (CWE)
References 7
https://github.com/pydantic/pydantic-ai/commit/394cc1d31656620704a703a2daed752a…
security-advisories@github.com
https://github.com/pydantic/pydantic-ai/commit/871c7aeec5dfed2138655ccbccbf15c6…
security-advisories@github.com
https://github.com/pydantic/pydantic-ai/pull/7437
security-advisories@github.com
https://github.com/pydantic/pydantic-ai/pull/7438
security-advisories@github.com
https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.5
security-advisories@github.com
https://github.com/pydantic/pydantic-ai/releases/tag/v2.30.0
security-advisories@github.com
https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-q2xc-rrxj-58x9
security-advisories@github.com