CVE-2026-107293
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.
Is your site exposed to CVE-2026-107293?
Run a free security scan — no signup, results in seconds.
Weakness Type (CWE)
References
Frequently Asked Questions
What is CVE-2026-107293? +
How do I check if I'm vulnerable to CVE-2026-107293? +
Related Vulnerabilities
Improper removal of sensitive information before storage or transfer vulnerability in Wikimedia Foundation's Mediawiki - FlaggedRevs extension through 1.46.0.
nebula-mesh is a self-hosted control plane for Slack Nebula mesh VPN. Prior to version 0.3.8, the web handler renderMobileBundle passes …
kube-audit-rest is a simple logger of mutation/creation requests to the k8s api. If the "full-elastic-stack" example vector configuration was used …
Grype is a vulnerability scanner for container images and filesystems. A credential disclosure vulnerability was found in Grype, affecting versions …
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.6 and …
Argo CD is a declarative, GitOps continuous delivery tool for Kubernetes. From versions 3.2.0 to before 3.2.11 and 3.3.0 to …