{"id":"CVE-2026-107286","revision":"5da7d5a576464b2d970c0677928b6974","records":[{"revision":"5da7d5a576464b2d970c0677928b6974","observedAt":"2026-10-23T15:48:27.903+00:00","statement":{"source":"cve-program","id":"CVE-2026-107286","aliases":[],"title":"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.","state":0,"publishedAt":"2026-10-08T15:12:26.597+00:00","modifiedAt":"2026-10-08T17:27:24.185+00:00","affected":[{"ecosystem":"Vendor product","name":"pydantic-ai","ranges":[],"versions":[],"rawVersionEvidence":"{\n                    \"vendor\": \"pydantic\",\n                    \"product\": \"pydantic-ai\",\n                    \"versions\": [\n                        {\n                            \"version\": \">= 2.10.0, < 2.53.0\",\n                            \"status\": \"affected\"\n                        }\n                    ]\n                }"},{"ecosystem":"Vendor product","name":"pydantic-ai-slim","ranges":[],"versions":[],"rawVersionEvidence":"{\n                    \"vendor\": \"pydantic\",\n                    \"product\": \"pydantic-ai-slim\",\n                    \"versions\": [\n                        {\n                            \"version\": \">= 2.10.0, < 2.53.0\",\n                            \"status\": \"affected\"\n                        }\n                    ]\n                }"}],"metrics":[{"system":"CVSS 3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","score":7.5,"severity":"HIGH"}],"references":["https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-6fqq-452j-qhrp","https://github.com/pydantic/pydantic-ai/pull/9478","https://github.com/pydantic/pydantic-ai/commit/453f19feeb7ab1d789f9393b1723c6a73b3d77b2","https://github.com/pydantic/pydantic-ai/releases/tag/v2.53.0"],"sourceUrl":"https://www.cve.org/CVERecord?id=CVE-2026-107286","license":"CVE Program Terms of Use","key":"cve-program:CVE-2026-107286","identifiers":["CVE-2026-107286"]},"retained":false,"historicalAffected":[]}],"coverage":[]}