CVE-2026-65975
6.5 · MEDIUMOverview
CVE-2026-65975 is a medium-severity vulnerability affecting pydantic pydantic_ai. It was published on July 29, 2026 and has a CVSS 3.1 base score of 6.5 (MEDIUM).
This vulnerability has a CVSS 3.1 base score of 6.5, rated MEDIUM. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.
Technical Description
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. In versions 1.88.0 up to but not including 1.107.1 and 2.0.0b1 up to but not including 2.5.0, the UI adapters (AG-UI via Agent.to_ag_ui()/AGUIAdapter, and Vercel AI via VercelAIAdapter) use sanitize_messages to strip unresolved ("dangling") client-submitted tool calls from untrusted message history before it reaches the agent, a defense-in-depth default that prevents the agent from executing tool calls the model never emitted. However, the strip anchored to a message index computed before sanitization ran, so when a trailing client message sanitized to empty and was dropped (for example a client system message under the default manage_system_prompt='server'), a preceding assistant response carrying an unresolved tool call became the new tail and was dispatched without inspection. As a result, a remote client could cause a registered, non-approval server tool to run with client-supplied a
Remediation
Check the references section for vendor advisories and patches from pydantic. Update pydantic_ai to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
Affected Products
| Vendor | Product | Versions | Status |
|---|---|---|---|
| pydantic | pydantic_ai | >= 1.88.0, < 1.107.1 | Affected |
Frequently Asked Questions
What is CVE-2026-65975?
CVE-2026-65975 is a medium-severity vulnerability affecting pydantic pydantic_ai. It was published on July 29, 2026 and has a CVSS 3.1 base score of 6.5 (MEDIUM).
How severe is CVE-2026-65975?
This vulnerability has a CVSS 3.1 base score of 6.5, rated MEDIUM. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.
How do I fix or remediate CVE-2026-65975?
Check the references section for vendor advisories and patches from pydantic. Update pydantic_ai to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
How can CyberStrike help with CVE-2026-65975?
CyberStrike's AI-powered security agents can automatically detect CVE-2026-65975 across your infrastructure using autonomous pentesting, DAST scanning, and HackBrowser. The platform continuously monitors for known vulnerabilities and provides actionable remediation guidance prioritized by real-world exploitability.
How CyberStrike Helps
AI agents map your attack surface to find vulnerabilities like this one.
Automated penetration testing that runs continuously, not just quarterly.
AI-driven PR review catches vulnerable dependencies before they ship.
Browser-based exploitation validates findings with real proof-of-concept.
Related MEDIUM CVEs from 2026
View all →Discourse is an open source discussion platform. In versions prior to 3.5.4, 2025.11.2, 2025.12.1, a
In libexpat before 2.7.4, the doContent function does not properly determine the buffer size bufSize
Buffer overflow vulnerability in the HDC module. Impact: Successful exploitation of this vulnerabili
ImageMagick is free and open-source software used for editing and manipulating digital images. Prior
A improper certificate validation vulnerability in Fortinet FortiAnalyzer 7.6.0 through 7.6.4, Forti
OpenClaw versions prior to 2026.3.1 fail to properly handle authentication bootstrap errors during s
File Browser is a file managing interface for uploading, deleting, previewing, renaming, and editing
Vulnerability of improper permission control in the theme setting module. Impact: Successful exploit
Access of resource using incompatible type ('type confusion') vulnerability in Samsung Open Source E
A flaw was found in Keycloak, specifically in the organization selection login page. A remote attack
Serendipity is a PHP-powered weblog engine. In versions 2.6-beta2 and below, the serendipity_setCoo
In iTerm2 through 3.6.9, displaying a .txt file can cause code execution via DCS 2000p and OSC 135 d