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

Advisory record · `GHSA-6fqq-452j-qhrp`

- **Identifiers:** `GHSA-6fqq-452j-qhrp` · `CVE-2026-107286` · `PYSEC-2026-4276` · `PYSEC-2026-4285`
- **State:** Confirmed
- **Severity:** CVSS 7.5 High
- **Critical:** No
- **Weakness (CWE):** [CWE-772](https://cwe.mitre.org/data/definitions/772.html)
- **Tags:** [Denial of service](https://agentprime.io/advisories/tag/dos.md)
- **Published:** 8 Oct 2026
- **Updated:** 15 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 8 Oct 2026, 19:42 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `pydantic-ai` (PyPI): affected `>=2.10.0, <2.53.0`; fixed in `2.53.0`
- `pydantic-ai-slim` (PyPI): affected `>=2.10.0, <2.53.0`; fixed in `2.53.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> Pydantic AI's concurrency-limited models (ConcurrencyLimitedModel and limit_model_concurrency) in pydantic-ai and pydantic-ai-slim versions 2.10.0 up to, but not including, 2.53.0 can permanently lose shared concurrency slots when a streamed request ends early or is fully consumed with default stream_text() debouncing. A remote client that repeatedly starts a stream and disconnects could eventually block later requests sharing the limiter. Upgrade to pydantic-ai or pydantic-ai-slim 2.53.0 or later; alternatively, use agent-level max_concurrency instead.

Written 1 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 7.5 High, CVSS 3.1: `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0045, the 39th percentile, on 8 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:08 UTC: First seen by agentprime
- 31 Oct 2026, 14:08 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-6fqq-452j-qhrp)

## Sources

- [GitHub Advisory Database: GHSA-6fqq-452j-qhrp](https://github.com/advisories/GHSA-6fqq-452j-qhrp)
- [OSV: GHSA-6fqq-452j-qhrp](https://osv.dev/vulnerability/GHSA-6fqq-452j-qhrp)
- <https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-6fqq-452j-qhrp>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-107286>
- <https://github.com/pydantic/pydantic-ai/pull/9478>
- <https://github.com/pydantic/pydantic-ai/commit/453f19feeb7ab1d789f9393b1723c6a73b3d77b2>
- <https://github.com/pydantic/pydantic-ai>
- <https://github.com/pydantic/pydantic-ai/releases/tag/v2.53.0>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-6fqq-452j-qhrp>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-6fqq-452j-qhrp/>. Everything for agents: <https://agentprime.io/llms.txt>.