| Package | Affected versions | Patched versions |
|---|---|---|
| pydantic-ai | ≥ 1.34.0, < 1.107.5≥ 2.0.0b1, < 2.30.0 | 1.107.52.30.0 |
| pydantic-ai-slim | ≥ 1.34.0, < 1.107.5≥ 2.0.0b1, < 2.30.0 | 1.107.52.30.0 |
| pydantic ai | ≥ 1.34.0, < 1.107.5≥ 2.0.0, < 2.30.0 | 1.107.52.30.0 |
The Pydantic AI development web chat UI (Agent.to_web(), clai web) does not validate the Host header of incoming requests. A website a developer visits can use DNS rebinding to make requests to a chat UI running on that developer's machine appear same-origin to the browser, causing the served agent to run and to execute its tools with the privileges and credentials of the local process.
Once a name the attacker controls resolves to the loopback address, the browser treats the request as same-origin, so neither an Origin check nor a CSRF token constrains it — a same-origin page can read the served UI and any token in it.
Binding the web UI to localhost — the default — does not prevent this.
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.
Current browser protections reduce but do not remove this exposure: Chromium's Local Network Access gates loopback subresource requests, but does not cover top-level navigations, and Safari does not implement it.
Upgrade to pydantic-ai/pydantic-ai-slim >= 2.30.0, or >= 1.107.5 on the v1 maintenance line.
The fix validates the Host header and rejects anything other than localhost, a loopback/LAN IP address, or an explicitly allowed host, responding 421 Misdirected Request otherwise. If you serve the web chat UI under a real hostname — behind a reverse proxy, tunnel, or similar — name it explicitly:
app = agent.to_web(allowed_hosts=['ui.example.com'])
Running one of these products? Scan your site to see whether it exposes a vulnerable version.
Scan my site free