CVE-2026-107291

Status: Received

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.

Published
October 8, 2026 5:17 PM
Last Modified
October 8, 2026 6:17 PM
Source
[email protected]

Weaknesses (CWE)

CWE-212 CWE-532

References

Contact Us

Get the CyboWatch SIEM platform, hosting, and 24×7 SOC analysts. Send an enquiry, or call or email us to get started.

Send an enquiry