Pydantic AI OpenTelemetry instrumentation: exception events on tool and agent run spans include content when `include_content=False`
pydantic-ai · pydantic-ai-slim
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| pydantic-ai PyPI |
|
|
| pydantic-ai-slim PyPI |
|
pydantic-ai · pydantic-ai-slim
| Product | Affected | Fixed in |
|---|---|---|
| pydantic-ai PyPI |
|
|
| pydantic-ai-slim PyPI |
|
|
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.
From the CVE record · GitHub_M
Pydantic AI and pydantic-ai-slim can export sensitive agent content despite OpenTelemetry being configured with InstrumentationSettings(include_content=False). Readers of the configured telemetry backend can see content in exception events, error status descriptions, and model request parameters; this does not grant new access to agent data. Deployments that do not use include_content=False are not affected by this setting bypass.
Check deployments using PyPI pydantic-ai or pydantic-ai-slim versions >=0.3.4 <1.107.6 or >=2.0.0b1 <2.44.0.