Disclosure summary
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.
Source-reported weakness categories
CWE-212, CWE-532
Source-specific records & product guidance
Sources retain their own attribution and scoring. Follow the original record to confirm affected versions, fixed releases, and configuration conditions.
NIST National Vulnerability Database · NVD-CVE-2026-107293
Open original source · Updated Oct 08, 2026
Only CPE matches marked vulnerable=true are indexed. AND/OR platform conditions must be checked in the original NVD record.
GitHub Reviewed Security Advisories · GHSA-3gh4-cghq-f8v4
Open original source · Updated Oct 08, 2026
Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`
Source severity: LOW / 2.3
| Ecosystem | Package | Affected range | First patched |
|---|---|---|---|
| pip | pydantic-ai | >= 0.3.4, < 1.107.4 | 1.107.4 |
| pip | pydantic-ai | >= 2.0.0b1, < 2.27.1 | 2.27.1 |
| pip | pydantic-ai-slim | >= 0.3.4, < 1.107.4 | 1.107.4 |
| pip | pydantic-ai-slim | >= 2.0.0b1, < 2.27.1 | 2.27.1 |
Original records & references
PUBLISHED 2026-10-08T13:17:14-04:00
MODIFIED 2026-10-08T16:35:31-04:00
INGESTED 2026-10-10T20:55:03-04:00