Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.4 and 2.27.1, OpenTelemetry instrumentation configured with InstrumentationSettings(include_content=False) can export retry prompts outside tool calls in gen_ai.input.messages and pydantic_ai.all_messages. Agents using NativeOutput, PromptedOutput, or output validators on text output can therefore disclose validation feedback, including invalid model values quoted by that feedback, to readers of the telemetry backend. Tool-call retries and deployments that do not use include_content=False are not affected by this specific path. This issue is fixed in versions 1.107.4 and 2.27.1.
Fix
Patch, vendor advisory and mitigation references on NVD 4
- https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441f6f5594f Patch
- https://github.com/pydantic/pydantic-ai/pull/7357 Patch, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1 Patch, Release Notes, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4 Mitigation, Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 1
- First seenCVSS 2.3 · pydanticNVD modified 2026-10-13 14:30
Affected (CPE criteria) 2
cpe:2.3:a:pydantic:pydantic_ai:*:*:*:*:*:python:*:*cpe:2.3:a:pydantic:pydantic_ai:*:-:*:*:*:python:*:*
References 4
- https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441f6f5594f Patch
- https://github.com/pydantic/pydantic-ai/pull/7357 Patch, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1 Patch, Release Notes, Vendor Advisory
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4 Mitigation, Vendor Advisory