Patch Forecast
Yellow warning
Plan into this sprint.

CVE-2026-107292 · GHSA-q2xc-rrxj-58x9

Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` header

Risk score
44/100
CVSS
6.4 v3.1
Exploit chance (30 days)
0.1%
Published
8 Oct 2026

Open in the live forecast Today's forecast

What to know

What it is
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 2.30.0, the Agent.to_web() and clai web development chat server does not validate the Host header, allowing a website visited by a developer to use DNS rebinding to reach a loopback-hosted agent as a s…
Affected
pydantic-ai (pip) >= 1.34.0, < 1.107.5; pydantic-ai (pip) >= 2.0.0b1, < 2.30.0; pydantic-ai-slim (pip) >= 1.34.0, < 1.107.5; pydantic-ai-slim (pip) >= 2.0.0b1, < 2.30.0
Fix
Upgrade pydantic-ai to 1.107.5 or 2.30.0; pydantic-ai-slim to 1.107.5 or 2.30.0 (whichever matches your release line) or later.
Exploitation
No known exploitation

Story map

Story map: pydantic-aiTHE FLAWSTHE FIXCVE-2026-107292Pydantic AI Web chat UI(`Agent.to_web()`, `clai web`):the local chat endpoint does…CVSS 6.4 · EPSS 0%CVE-2026-107286Pydantic AI:Concurrency-limited modelscan keep their slot when a…CVSS 7.5 · EPSS 0%CVE-2026-107295Pydantic AI Web chat UI(`Agent.to_web()`, `clai web`):a website visited by the…CVSS 7.6 · EPSS 0%CVE-2026-107290Pydantic AI: Event loop blockedby quadratic title extraction in`web_fetch`CVSS 6.5 · EPSS 0%Upgrade pydantic-ai1.107.5 · 2.30.0 · 2.53.0 · 1.107.4· 2.28.0 · 1.107.6or later on your release lineWho is exposedpydantic-ai (pip) >= 2.10.0, <2.53.0; pydantic-ai-slim (pip)>= 2.10.0, < 2.53.0AMBER · PATCH THIS WEEKpydantic-aiPydantic AI is a Python agentframework for buildingapplications and workflows withGenerative AI. From 2.10.0 until2.53.0, streamed requests madethroughConcurrencyLimitedModel or…Where it standsPublic proof of conceptCONNECTS TOSame weaknessCWE-346 (CWE-346)54 other warnings in 30 days →Same productEarlier pydantic-ai warnings6 in the last 90 days →
Story map: the flaws, the fix, how it unfolded and what it connects to. Boxes link to the record or article.

At a glance

pydantic-ai: Amber, patch this week. Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 2.10.0 until 2.53.0, streamed requests made through ConcurrencyLimitedModel or limit_model_concurrency can retain shared concurrency slots because anyio.CapacityLimiter associates an acquired slot with the borrowin…

The flaws

  • CVE-2026-107292: Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): the local chat endpoint does not validate the `Host` header (CVSS 6.4 · EPSS 0%)
  • CVE-2026-107286: Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early (CVSS 7.5 · EPSS 0%)
  • 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 (CVSS 7.6 · EPSS 0%)
  • CVE-2026-107290: Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch` (CVSS 6.5 · EPSS 0%)

The fix

Upgrade pydantic-ai: 1.107.5 · 2.30.0 · 2.53.0 · 1.107.4 · 2.28.0 · 1.107.6 or later on your release line

Who is exposed: pydantic-ai (pip) >= 2.10.0, < 2.53.0; pydantic-ai-slim (pip) >= 2.10.0, < 2.53.0

Where it stands

  • Public proof of concept

Connects to

Why it is Yellow

  • CVSS 6.4 medium
  • On your watchlist: PyPI

Affected packages

PackageEcosystemVulnerableFixed in
pydantic-aipip>= 1.34.0, < 1.107.51.107.5
pydantic-aipip>= 2.0.0b1, < 2.30.02.30.0
pydantic-ai-slimpip>= 1.34.0, < 1.107.51.107.5
pydantic-ai-slimpip>= 2.0.0b1, < 2.30.02.30.0

References

Original description

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 2.30.0, the Agent.to_web() and clai web development chat server does not validate the Host header, allowing a website visited by a developer to use DNS rebinding to reach a loopback-hosted agent as a same-origin service. The hostile page can read the served UI and submit chat requests that execute agent tools with the local process's privileges and credentials, causing data disclosure or unwanted side effects. Binding to localhost, Origin checks, and CSRF tokens do not prevent the same-origin DNS rebinding path. This issue is fixed in versions 1.107.5 and 2.30.0.

Last activity 8 Oct 2026. Patch Forecast updates every hour.