cyfenced.com →

[ CVE-2026-107293 · Published 8 Oct 2026 ]

Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`

CVSS 5.3 EPSS <1%Fix available

[ Description ]Official description

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.

[ Fixes ]Fixes and patches

  • pydantic-ai 1.107.4Fixed version · GitHub Advisories · pip package pydantic-ai: upgrade to 1.107.4 or later (affected >= 0.3.4, < 1.107.4)
  • pydantic-ai 2.27.1Fixed version · GitHub Advisories · pip package pydantic-ai: upgrade to 2.27.1 or later (affected >= 2.0.0b1, < 2.27.1)
  • pydantic-ai-slim 1.107.4Fixed version · GitHub Advisories · pip package pydantic-ai-slim: upgrade to 1.107.4 or later (affected >= 0.3.4, < 1.107.4)
  • pydantic-ai-slim 2.27.1Fixed version · GitHub Advisories · pip package pydantic-ai-slim: upgrade to 2.27.1 or later (affected >= 2.0.0b1, < 2.27.1)
  • Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD
  • Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD
  • Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD

[ Packages ]Affected open-source packages

[ References ]References