Skip to content
fr Sign in
2.3 Low

CVE-2026-107291 Pydantic AI is a Python agent framework for building applications and workflows with Generative AI

Description

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.6 and 2.44.0, OpenTelemetry instrumentation configured with InstrumentationSettings(include_content=False) can still export sensitive agent content through exception.message and exception.stacktrace events, error status descriptions, and model_request_parameters containing instructions or the prompted_output_template. The exposed data is available to readers of the configured telemetry backend and can include tool feedback, provider error bodies, runtime instructions, and structured-output templates even though message attributes are redacted. This issue does not grant new access to agent data, and deployments that do not use include_content=False are not affected by the setting bypass. This issue is fixed in versions 1.107.6 and 2.44.0.

Affected products and versions

Product Affected versions Fixed in
pydantic-ai 2.0 2.0.0b1 → < 2.44.0 2.44.0
pydantic-ai 0.3 0.3.4 → < 1.107.6 1.107.6
pydantic-ai-slim 2.0 2.0.0b1 → < 2.44.0 2.44.0
pydantic-ai-slim 0.3 0.3.4 → < 1.107.6 1.107.6

References

Timeline

  1. Published
  2. Last modified

Other CVEs of pydantic-ai

The 16 CVEs of pydantic-ai →
CVE-2026-107295 Pydantic AI is a Python agent framework for building applications and workflows with Generative AI 7.6 High CVE-2026-107294 Pydantic AI is a Python agent framework for building applications and workflows with Generative AI 6.5 Medium CVE-2026-107293 Pydantic AI is a Python agent framework for building applications and workflows with Generative AI 2.3 Low CVE-2026-107292 Pydantic AI is a Python agent framework for building applications and workflows with Generative AI 6.4 Medium
Track this CVE