PT-2026-65900 · Pydantic · Pydantic-Ai+1
CVE-2026-65975
·
Published
2026-07-29
·
Updated
2026-07-29
CVSS v3.1
6.5
Medium
| Vector | AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N |
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.
Fix
Incorrect Authorization
Found an issue in the description? Have something to add? Feel free to write us 👾
Weakness Enumeration
Related Identifiers
Affected Products
Pydantic-Ai
Pydantic-Ai-Slim