GHSA-4x9p-g9wm-8q7f: Pip/pydantic-ai-slim vulnerability

Published Oct 8, 2026
·
Updated

Summary

Pydantic AI's OpenTelemetry instrumentation supports InstrumentationSettings(includecontent=False) to exclude message content — user prompts, model completions, tool call arguments and responses, and any other message content — from exported telemetry, so that agents can be monitored without sending sensitive content to the observability backend.

The message attributes honoured the setting. Several other parts of the same spans did not, and exported content regardless of it:

- Exceptions. Recorded as OpenTelemetry exception events, with their message and stack trace, on tool, agent run, model request, embedding and image generation spans, and on realtime session spans. The message of the exception carrying a tool's ModelRetry or ToolFailed feedback is the text sent back to the model, which can quote tool arguments and results. When a tool ran out of retries, the error that ended the run was chained from the last retry, so its stack trace repeated that text on the run span. Exceptions raised by tool code were recorded with their full message, as were failures of a model request, embedding or image generation, whose messages carry the provider's error response body. - The error status description. The OpenTelemetry SDK describes a span's ERROR status with the exception's type and message, so the message reached the backend a second time even where the event itself was redacted. - Instructions and the prompted-output template. The modelrequestparameters attribute serialized the request's instruction parts in full, exporting the agent's instructions — both static and those built from dependencies at request time — along with the template used to prompt for structured output.

Details

Content reaches these places because of what they carry rather than through any single missing check, which is why the setting was applied correctly to the message attributes (genai.input.messages, genai.tool.call.arguments, genai.tool.call.result, and so on) while these paths were not: the exception recording and the status description came from the OpenTelemetry SDK's defaults, and the instructions and output template were serialized as part of the request's parameters rather than treated as content.

Impact

This does not grant an attacker any new access to the agent or its data: the content is only visible to whoever can read the exported telemetry. The exposure matters when traces are exported to a destination whose audience is broader or less trusted than the agent's own data — a third-party observability vendor or a shared backend — which is the scenario includecontent=False exists for.

Who Is Affected

You are affected if you enabled instrumentation with includecontent=False. Instructions are exported on every successful run, so no failure is needed to be affected; the exception paths additionally require a tool to raise, or a model, embedding or image generation request to fail. Realtime sessions are affected the same way, through the errors their provider connections report. GHSA-3gh4-cghq-f8v4 stated that retries coming from tool calls were redacted correctly; that was true of the retry prompt in the message attributes but not of the exception event on the tool span. You are not affected if you don't set includecontent=False.

Remediation

Upgrade to a patched version. With includecontent=False, exception events now record only the exception type, error statuses carry no description, and modelrequestparameters is exported without its instruction content or output template. If you rely on this setting, consider reviewing previously exported traces for exception events, for error status descriptions, and for modelrequestparameters.

Workaround for Unpatched Versions

If you cannot upgrade, scrub the exception.message and exception.stacktrace event attributes, the error status description, and the instruction parts and promptedoutputtemplate within modelrequestparameters, on spans emitted by Pydantic AI in your telemetry pipeline (for example with an OpenTelemetry Collector processor). Setting includemodelrequestparameters=False alongside includecontent=False removes both, at the cost of the rest of that attribute.

Credits

Reported privately by @BrianWillows, whose report covered the exception events on tool and agent run spans. The remaining paths were found while fixing it, by a test that drives content through every channel at once and checks the whole exported trace.

Affected Software

4 affected componentsFixes available
pip/pydantic-ai-slim>=2.0.0b1<2.44.0
2.44.0
pip/pydantic-ai-slim>=0.3.4<1.107.6
1.107.6
pip/pydantic-ai>=2.0.0b1<2.44.0
2.44.0
pip/pydantic-ai>=0.3.4<1.107.6
1.107.6

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade pip/pydantic-ai-slim to a version that resolves this vulnerability.

    Fixed in 2.44.0
  2. Upgrade

    Upgrade pip/pydantic-ai-slim to a version that resolves this vulnerability.

    Fixed in 1.107.6
  3. Upgrade

    Upgrade pip/pydantic-ai to a version that resolves this vulnerability.

    Fixed in 2.44.0
  4. Upgrade

    Upgrade pip/pydantic-ai to a version that resolves this vulnerability.

    Fixed in 1.107.6
  5. Configuration

    Configure InstrumentationSettings with include_content=False and set include_model_request_parameters=False to exclude message content, instruction parts, and prompted_output_template from exported telemetry.

    Pydantic AI OpenTelemetry instrumentation include_content=False; include_model_request_parameters=False = false
  6. Compensating control

    In the OpenTelemetry telemetry pipeline, scrub exception.message and exception.stacktrace event attributes, the error status description, and the instruction parts and prompted_output_template within model_request_parameters on spans emitted by Pydantic AI.

  7. Operational

    Review previously exported traces for exception events, error status descriptions, and model_request_parameters for potentially exposed content.

Event History

Oct 8, 2026
Advisory Published
via GitHub·04:48 PM
Data Sourced
via GitHub·04:48 PM
DescriptionWeaknessAffected Software

Frequently Asked Questions

1

Who is exposed to this issue?

Deployments using Pydantic AI OpenTelemetry instrumentation and relying on InstrumentationSettings(include_content=False) to keep message content out of their observability backend are exposed. The setting is honored for message attributes but not for several other span fields.

2

What content can still reach the telemetry backend?

Exception messages and stack traces may contain sensitive content. This includes tool ModelRetry or ToolFailed feedback sent back to the model, tool arguments and results quoted in that feedback, tool-code exception messages, and provider error responses from failed model, embedding, or image-generation requests.

3

How can I check whether telemetry may contain leaked content?

Review exported OpenTelemetry spans for recorded exception events, including their exception messages and stack traces. Check tool, agent-run, model-request, embedding, image-generation, and realtime-session spans, with particular attention to retry exhaustion because the ending error's chained stack trace can repeat the last retry text.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203