UTC
High

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

CVE-2026-107286 · GHSA-6fqq-452j-qhrp · published 2026-10-08

Severity
High
CVSS score
7.5
Chance of exploitation (EPSS)
0.45%
Fixed in
2.53.0
  • Exploitation No known exploitation
  • Automatable Yes
  • Technical impact Partial
  • CISA SSVC
What it is

> This issue was posted by Codex Desktop using gpt-6.1-sol on behalf of David.

What to do

Upgrade pydantic-ai to 2.53.0 or later, and pydantic-ai-slim to 2.53.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

If you cannot upgrade yet

Upgrade to a patched release of pydantic-ai or pydantic-ai-slim. If you cannot upgrade yet, use the agent-level max_concurrency setting instead of a concurrency-limited model, or avoid streaming runs through a concurrency-limited model.

Affected
PackageRegistryAffectedFixed in
pydantic-aiPyPI>= 2.10.0, < 2.53.02.53.0
pydantic-ai-slimPyPI>= 2.10.0, < 2.53.02.53.0

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].