CVE-2026-65975
Last modified
CVE-2026-65975 is a medium-severity vulnerability rated 6.5/10 on the CVSS scale. 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. EPSS estimates a 0.21% chance of exploitation in the next 30 days.
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 arguments rather than arguments the model produced. The impact is bounded by what the affected tools do and is most significant for applications that gate tool execution in a model-request hook (before_model_request / after_model_request), since a forged call skips the model turn and bypasses that guardrail; approval-gated tools (requires_approval=True) are not auto-executed by this path. This issue has been fixed in versions 1.107.1 and 2.5.0.
Metrics
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Pydantic | Pydantic Ai | >= 1.88.0, < 1.107.1 |
| Pydantic | Pydantic Ai | >= 2.0.0, < 2.5.0 |
References
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-65975?
How severe is CVE-2026-65975?
How do I fix CVE-2026-65975?
How Strix Helps
- Uncovering a hidden BOLA in Appsmith's snapshot logicStrix autonomously discovered a BOLA/IDOR vulnerability in Appsmith's snapshot deletion path.
- Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
- PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
- AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.
Related CVEs from 2026
- CVE-2026-65959Vitess is a database clustering system for horizontal scalin…5.3
- CVE-2026-6596A security flaw has been discovered in langflow-ai langflow …7.3
- CVE-2026-65969OpenImageIO is a toolset for reading, writing, and manipulat…5.5
- CVE-2026-6597A weakness has been identified in langflow-ai langflow up to…2.7
- CVE-2026-65970OpenImageIO is a toolset for reading, writing, and manipulat…5.3
- CVE-2026-65974ERPNext is a free and open source Enterprise Resource Planni…9.9
- CVE-2026-65976Deskflow is a keyboard and mouse sharing app. From 1.17.0 un…6.5
- CVE-2026-65979OpenEXR is the reference implementation and specification fo…6.7
- CVE-2026-6598A security vulnerability has been detected in langflow-ai la…4.3
- CVE-2026-65980Chartbrew is an open-source web application that can connect…7.9
- CVE-2026-65981Coturn is a free open source implementation of TURN and STUN…7.1
- CVE-2026-65984FUXA is a web-based Process Visualization (SCADA/HMI/Dashboa…7.5
Are you affected by CVE-2026-65975?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
