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
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)
Czego dotyczy
Kliknij technologię, aby zobaczyć wszystkie dotyczące jej podatności.
| Platforma | Paczka | Podatne wersje | Poprawka w wersji |
|---|---|---|---|
| Python (PyPI) | pydantic-ai | >= 1.34.0, < 1.107.4, >= 2.0.0b1, < 2.28.0 | 1.107.4, 2.28.0 |
| Python (PyPI) | pydantic-ai-slim | >= 1.34.0, < 1.107.4, >= 2.0.0b1, < 2.28.0 | 1.107.4, 2.28.0 |
Odnośniki
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93
- https://github.com/pydantic/pydantic-ai/pull/7382
- https://github.com/pydantic/pydantic-ai/pull/7383
- https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46
- https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0
- https://github.com/pydantic/pydantic-ai
- https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0
- https://pypi.org/project/pydantic-ai
- https://github.com/advisories/GHSA-h4xc-3qfq-jf93
- https://nvd.nist.gov/vuln/detail/CVE-2026-107295
- https://pypi.org/project/pydantic-ai-slim
- Wektor CVSS
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L- Słabość (CWE)
CWE-346, CWE-352- Platforma
- Python (PyPI)
- Paczka
pydantic-ai, pydantic-ai-slim- Ujawniono
- 08.10.2026
- Aktualizacja
- 15.10.2026 18:17
Źródła i licencje
OSV / GitHub Advisory Database - PYSEC-2026-4278 - PyPA Advisory Database; CC BY 4.0
OSV / GitHub Advisory Database - GHSA-h4xc-3qfq-jf93 - CC BY 4.0
OSV / GitHub Advisory Database - PYSEC-2026-4287 - PyPA Advisory Database; CC BY 4.0
Historia podatności: pydantic-ai
Wszystkie opisane podatności tej paczki (Python (PyPI)), od najnowszej. Widać, czy to jednorazowa wpadka, czy paczka, której trzeba pilnować.
- Wszystkich wpisów
- 14
- Pierwsza → ostatnia
- 02.2026 10.2026
- Bez poprawki
- 0
- Wykorzystywana w atakach
- 0
Rozkład istotności
- Wysoka 4
- Średnia 8
- Niska 2
Ujawnienia w latach
- 2026: 14
-
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 ten wpis
Dowiedz się, które podatności dotyczą Twojej aplikacji
Po podłączeniu integracji DockRay i włączeniu raportowania oprogramowania DockRay porównuje zgłoszone wersje komponentów ze znanymi podatnościami i powiadamia o potwierdzonych dopasowaniach. Zakres zależy od obsługiwanej technologii i dostępnych biuletynów.