What’s Vulnerable › Vulnerabilities

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

• Severity: high (CVSS 7.5 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.4% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-10-08 · updated 2026-10-13
• Weakness: CWE-772

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.

Affected products

• pydantic-ai: from 2.10.0 before 2.53.0 — fixed in 2.53.0

How to fix

Upgrade to a fixed version: pydantic-ai 2.53.0. Check the vendor advisory for mitigations.

References

• https://github.com/pydantic/pydantic-ai/commit/453f19feeb7ab1d789f9393b1723c6a73b3d77b2
• https://github.com/pydantic/pydantic-ai/pull/9478
• https://github.com/pydantic/pydantic-ai/releases/tag/v2.53.0
• https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-6fqq-452j-qhrp

Get alerted when CVE-2026-107286 or the next vulnerability affects your stack