CVE-2026-107293

What it is

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.

At a glance

Exploitability

Can be exploited over the network with a low-privilege account. Limited direct impact.

Exploit odds

0.3% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-10-08 17:17 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-10-13 14:30 UTC Last updatedMost recent change to the record

Details

Published

2026-10-08 17:17 UTC

Last modified

2026-10-13 14:30 UTC

Exploit probability

0.3% · EPSS, next 30 days

Weakness

CWE-212

Record status

Analyzed

Affected

• Pydantic Ai < 1.107.4
• Pydantic Ai < 2.27.1

Attack profile CVSS 4.0 · 2.3

Attack vector

Network

Complexity

Low

Attack requirements

Present

Privileges needed

Low

User interaction

None

Confidentiality

Low

Integrity

None

Availability

None