CVE-2026-107291

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.

• CWE-212
• CWE-532

• https://github.com/pydantic/pydantic-ai/commit/4e013c51a50659aba2adf7853bfb22bb77f6a518
• https://github.com/pydantic/pydantic-ai/commit/6b14c74cb281f899a2ae4fae5327111e33f60771
• https://github.com/pydantic/pydantic-ai/commit/7ee27e38ab2e525ca60ff1a25d16413ff989fd79
• https://github.com/pydantic/pydantic-ai/commit/963dec5f70d6f558997fc259356c0090cc5ea487
• https://github.com/pydantic/pydantic-ai/commit/de4e61515327bd80a19cd8552001c30933e6acc3
• https://github.com/pydantic/pydantic-ai/pull/8403
• https://github.com/pydantic/pydantic-ai/pull/8404
• https://github.com/pydantic/pydantic-ai/pull/8408
• https://github.com/pydantic/pydantic-ai/pull/8428
• https://github.com/pydantic/pydantic-ai/pull/8429
• https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.6
• https://github.com/pydantic/pydantic-ai/releases/tag/v2.44.0
• https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-4x9p-g9wm-8q7f

Published

Oct 8, 2026

Last Modified

Oct 8, 2026

Status

Awaiting Analysis

• How Strix found a critical auth bypass in etcdStrix autonomously discovered a critical authentication bypass in etcd, later designated CVE-2026-33413.
• Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
• PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
• AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.

• CVE-2026-107286Pydantic AI is a Python agent framework for building applica…7.5
• CVE-2026-107287Pydantic AI is a Python agent framework for building applica…6.5
• CVE-2026-107288Pydantic AI is a Python agent framework for building applica…3.7
• CVE-2026-107289Pydantic AI is a Python agent framework for building applica…6.8
• CVE-2026-10729An HTML injection vulnerability in the notification email fo…1.2
• CVE-2026-107290Pydantic AI is a Python agent framework for building applica…6.5
• CVE-2026-107292Pydantic AI is a Python agent framework for building applica…6.4
• CVE-2026-107293Pydantic AI is a Python agent framework for building applica…2.3
• CVE-2026-107294Pydantic AI is a Python agent framework for building applica…6.5
• CVE-2026-107295Pydantic AI is a Python agent framework for building applica…7.6
• CVE-2026-107296msgpack5 is a msgpack v5 implementation for node.js and the …3.7
• CVE-2026-107297msgpack5 is a msgpack v5 implementation for node.js and the …5.9