CVE-2026-107293
LOW
2,3
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
Description
AI Translation Available
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.
212
Improper Removal of Sensitive Information Before Storage or Transfer
IncompleteCommon Consequences
Security Scopes Affected:
Confidentiality
Potential Impacts:
Read Files Or Directories
Read Application Data
Applicable Platforms
All platforms may be affected
532
Insertion of Sensitive Information into Log File
IncompleteCommon Consequences
Security Scopes Affected:
Confidentiality
Potential Impacts:
Read Application Data
Applicable Platforms
All platforms may be affected
https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441…
https://github.com/pydantic/pydantic-ai/pull/7357
https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1
https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4