Incorrect Authorization Affecting pydantic-ai-slim package, versions [1.88.0,1.107.1)[2.0.0b1,2.5.0)
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applicationsSnyk Learn
Learn about Incorrect Authorization vulnerabilities in an interactive lesson.
Start learning- Snyk IDSNYK-PYTHON-PYDANTICAISLIM-20877472
- published13 Oct 2026
- disclosed29 Jul 2026
- creditUnknown
Introduced: 29 Jul 2026
CVE-2026-65975 (opens in a new tab)How to fix?
Upgrade pydantic-ai-slim to version 1.107.1, 2.5.0 or higher.
Overview
pydantic-ai-slim is an Agent Framework / shim to use Pydantic with LLMs, slim package
Affected versions of this package are vulnerable to Incorrect Authorization in the sanitize_messages process. An attacker can trigger execution of a registered server tool with client-supplied arguments by submitting a crafted message sequence that causes a trailing client message to be dropped, resulting in a preceding assistant response with an unresolved tool call being dispatched without proper inspection. This can allow bypassing of model-request hooks that normally gate tool execution. This is only exploitable if the application uses non-approval server tools and relies on model-request hooks for gating tool execution.