GHSA-h4xc-3qfq-jf93: CSRF
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.
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.toweb() 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 requiresapproval=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)
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
pip/pydantic-ai-slimto a version that resolves this vulnerability.Fixed in 2.28.0 - Upgrade
Upgrade
pip/pydantic-ai-slimto a version that resolves this vulnerability.Fixed in 1.107.4 - Upgrade
Upgrade
pip/pydantic-aito a version that resolves this vulnerability.Fixed in 2.28.0 - Upgrade
Upgrade
pip/pydantic-aito a version that resolves this vulnerability.Fixed in 1.107.4 - Compensating control
If you cannot upgrade, do not run the Pydantic AI development web UI (`Agent.to_web()` or `clai web`) while browsing untrusted sites.
- Compensating control
Stop the Pydantic AI development web UI (`Agent.to_web()` or `clai web`) when it is not in use.
- Compensating control
Do not serve an agent with side-effecting tools through the Pydantic AI development web UI (`Agent.to_web()` or `clai web`).
Event History
Frequently Asked Questions
Does binding the chat UI to localhost prevent exploitation?
No. Localhost binding is the default, but a website open in the developer's browser can reach the loopback address and submit requests to the local chat endpoint.
Who is exposed to this issue?
Applications and developers serving an agent through Agent.to_web() or clai web are affected. Exploitation requires a developer to visit a website that submits a request to the running chat UI.
Are tools requiring approval protected from this attack?
No. Tools marked requires_approval=True were not protected because the endpoint trusted approval decisions relayed by the client.
What are the consequences if exploitation succeeds?
The served agent can run its tools with the privileges and credentials of the local process. Depending on the exposed tools, this can cause data disclosure and unwanted tool side effects.
What changes after upgrading?
The patched chat endpoint requires Content-Type: application/json and rejects other requests before parsing the body or running the agent. The bundled chat UI already sends this header.