Bug 2548063 (CVE-2026-107295)

Summary:	CVE-2026-107295 pydantic-ai-slim: pydantic-ai-slim: Unauthorized tool execution via missing Content-Type validation
Product:	[Other] Security Response	Reporter:	OSIDB Bzimport <bzimport>
Component:	vulnerability	Assignee:	Product Security DevOps Team <prodsec-dev>
Status:	NEW ---	QA Contact:
Severity:	high	Docs Contact:
Priority:	high
Version:	unspecified	CC:	ebourniv, hasun, nyancey, ptisnovs, sbunciak
Target Milestone:	---	Keywords:	Security
Target Release:	---
Hardware:	All
OS:	Linux
Whiteboard:
Fixed In Version:		Doc Type:	---
Doc Text:	A flaw was found in pydantic-ai-slim. The local development chat interface does not properly validate request content types, allowing a malicious website visited by a developer to send cross-origin requests to the locally hosted server. A remote attacker can exploit this vulnerability to trigger unauthorized tool execution with the privileges and credentials of the local process, bypassing required approval controls.	Story Points:	---
Clone Of:		Environment:
Last Closed:		Type:	---
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2026-10-08 17:21:25 UTC

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 1.107.4 and 2.28.0, the Agent.to_web() and clai web development chat endpoint has missing request content-type validation. A website visited by a developer can submit a browser-compatible request to a loopback-hosted chat server, causing the served agent to run and execute tools with the privileges and credentials of the local process; client-relayed approval decisions also leave requires_approval=True tools exposed. Binding to localhost does not prevent a browser page from reaching the loopback address. This issue is fixed in versions 1.107.4 and 2.28.0.