CVE-2026-107291: Pydantic AI OpenTelemetry instrumentation: exception events on tool and agent run spans include content when `include_content=False`

Severity: medium (CVSS 4.3 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.6% probability of exploitation in the next 30 days
Public exploit or detection template: yes
Published: 2026-10-08 · updated 2026-10-13
Weakness: CWE-212

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

pydantic-ai: from 0.3.4 before 1.107.4; from 2.0.0 before 2.44.0 — fixed in 1.107.4, 2.44.0

How to fix

Upgrade to a fixed version: pydantic-ai 1.107.4, 2.44.0. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2026-107291 or the next vulnerability affects your stack