Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · Pydantic AI

CVE-2026-107295: 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

highCVSS 3.1 7.6GHSA-h4xc-3qfq-jf93

Summary The Pydantic AI development web chat UI (Agent.toweb(), clai web) did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute its tools with the privileges and credentials of the local process.

Published Oct 8, 2026

Affected packages

pydantic-ai

Ecosystem
PyPI
Affected
>= 1.34.0, < 1.107.4
Fixed in
1.107.4
Check
pip show pydantic-ai

pydantic-ai

Ecosystem
PyPI
Affected
>= 2.0.0b1, < 2.28.0
Fixed in
2.28.0
Check
pip show pydantic-ai

pydantic-ai-slim

Ecosystem
PyPI
Affected
>= 1.34.0, < 1.107.4
Fixed in
1.107.4
Check
pip show pydantic-ai-slim

pydantic-ai-slim

Ecosystem
PyPI
Affected
>= 2.0.0b1, < 2.28.0
Fixed in
2.28.0
Check
pip show pydantic-ai-slim

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Summary

The Pydantic AI development web chat UI (Agent.to_web(), clai web) did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute its tools with the privileges and credentials of the local process.

Binding the web UI to localhost — the default — does not prevent this, because a page open in the developer's browser can reach the loopback address.

Impact

Applications and developers serving an agent through Agent.to_web() or clai web. The consequences depend on the tools the served agent exposes, and can include data disclosure as well as unwanted tool side effects. Tools marked requires_approval=True were not protected either, because the endpoint trusts approval decisions relayed by the client.

Mitigation

Upgrade to a patched version. The chat endpoint now requires Content-Type: application/json and rejects other requests before the request body is parsed and before the agent runs. The bundled chat UI already sends this header; scripts and other non-browser clients that call the endpoint directly may need to be updated to send it.

If you cannot upgrade, don't run the web UI while browsing untrusted sites, stop it when you aren't using it, and don't serve an agent with side-effecting tools through it.

Credits

  • Thai Son Dinh from VinSOC Labs (R&D)

Credited to sondt99.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More Pydantic AI vulnerabilities

All Pydantic AI entries