Disclosure summary
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.
Source-reported weakness categories
CWE-352
Source-specific records & product guidance
Sources retain their own attribution and scoring. Follow the original record to confirm affected versions, fixed releases, and configuration conditions.
NIST National Vulnerability Database · NVD-CVE-2026-107295
Open original source · Updated Oct 08, 2026
Only CPE matches marked vulnerable=true are indexed. AND/OR platform conditions must be checked in the original NVD record.
GitHub Reviewed Security Advisories · GHSA-h4xc-3qfq-jf93
Open original source · Updated Oct 08, 2026
Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint
Source severity: HIGH / 0
| Ecosystem | Package | Affected range | First patched |
|---|---|---|---|
| pip | pydantic-ai | >= 1.34.0, < 1.107.4 | 1.107.4 |
| pip | pydantic-ai | >= 2.0.0b1, < 2.28.0 | 2.28.0 |
| pip | pydantic-ai-slim | >= 1.34.0, < 1.107.4 | 1.107.4 |
| pip | pydantic-ai-slim | >= 2.0.0b1, < 2.28.0 | 2.28.0 |
Original records & references
- NIST NVD record
- CVE Program record
- github.com
- github.com
- github.com
- github.com
- github.com
- github.com
- github.com
PUBLISHED 2026-10-08T13:17:15-04:00
MODIFIED 2026-10-08T16:35:31-04:00
INGESTED 2026-10-10T20:55:03-04:00