PoC Monitor
← All CVEs
CVE-2026-107286published 8 Oct 2026 15:12 UTCData: JSON · API

Pydantic pydantic-ai

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

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.

First public PoC None yetno public PoC found
Public PoCs00 on GitHub
CVSS7.5high · scored by CNA · CWE-772
CISA KEV Not listednot known exploited

Affected versions and mitigation

From the CVE record and the vendor's references.

Affected

pydantic pydantic-ai
  • >= 2.10.0, < 2.53.0

Fixed in 2.53.0

pydantic pydantic-ai-slim
  • >= 2.10.0, < 2.53.0

Fixed in 2.53.0

Mitigation

Upgrade pydantic-ai to 2.53.0 or later.

Upgrade pydantic-ai-slim to 2.53.0 or later.

References

1 more

Timeline

Days relative to CVE publication
-2t=0+2+4+6+8CVE published8 Oct 2026 · t = 0

No public PoC found yet; not in CISA KEV.

PoC repositories

Found on GitHub.

No PoC repositories found yet.