7.5
HIGH CVSS 3.1
CVE-2026-107286
Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early
Description

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 borrowing task while streaming cleanup can run in a different task. Early stream termination, cancellation, consumer exceptions, or complete stream_text() consumption with debounce_by=0.1 can therefore leave capacity occupied, eventually preventing later requests that share the long-lived limiter from proceeding and causing a denial of service. Agent-level max_concurrency and non-streaming model requests are not affected. This issue is fixed in version 2.53.0.

INFO

Published Date :

Oct. 8, 2026, 3:17 p.m.

Last Modified :

Oct. 8, 2026, 8:35 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2026-107286 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

ID Vendor Product Action
1 Pydantic pydantic_ai
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 134c704f-9b21-4f2e-91b3-4a467353bcc0
CVSS 3.1 HIGH [email protected]
Solution
Update Pydantic AI to version 2.53.0 or later to fix concurrency slot issues.
  • Update Pydantic AI to version 2.53.0.
  • Ensure agent-level max_concurrency is configured.
  • Monitor streaming model request behavior.
References to Advisories, Solutions, and Tools
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-107286 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-107286 weaknesses.

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-107286 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-107286 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0

    Oct. 08, 2026

    Action Type Old Value New Value
    Added SSVC {'id': 'CVE-2026-107286', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'none'}, {'automatable': 'yes'}, {'technicalImpact': 'partial'}], 'version': '2.0.3', 'timestamp': '2026-10-08T17:26:50.651820Z'}
  • New CVE Received by [email protected]

    Oct. 08, 2026

    Action Type Old Value New Value
    Added Description 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 borrowing task while streaming cleanup can run in a different task. Early stream termination, cancellation, consumer exceptions, or complete stream_text() consumption with debounce_by=0.1 can therefore leave capacity occupied, eventually preventing later requests that share the long-lived limiter from proceeding and causing a denial of service. Agent-level max_concurrency and non-streaming model requests are not affected. This issue is fixed in version 2.53.0.
    Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
    Added CWE CWE-772
    Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/107xxx/CVE-2026-107286.json">CVE-2026-107286</a>
    Added Reference https://github.com/pydantic/pydantic-ai/commit/453f19feeb7ab1d789f9393b1723c6a73b3d77b2
    Added Reference https://github.com/pydantic/pydantic-ai/pull/9478
    Added Reference https://github.com/pydantic/pydantic-ai/releases/tag/v2.53.0
    Added Reference https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-6fqq-452j-qhrp
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.