CVE-2026-107293

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

State: Published
Severity: 2.3 Low
Published: Oct 8, 2026
Updated: Oct 8, 2026
Reserved: Oct 7, 2026

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.

Scores

CVSS	Score	Vector	Source
4.0	2.3 Low	CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N	GitHub_M

Weaknesses

CWE-212 Improper Removal of Sensitive Information Before Storage or Transfer
CWE-532 Insertion of Sensitive Information into Log File

Affected Products

Product	Versions
pydantic-aipydantic	>= 0.3.4, < 1.107.4Affected >= 2.0.0b1, < 2.27.1Affected
pydantic-ai-slimpydantic	>= 0.3.4, < 1.107.4Affected >= 2.0.0b1, < 2.27.1Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.