AIKIDO-2026-154836
pydantic-ai-slim is vulnerable to Exposure of Sensitive Information
23
Low Risk
This Affects:
pydantic-ai-slimTL;DR
Pydantic AI's OpenTelemetry instrumentation supports excluding message content from exported telemetry through include_content=False. Retry prompts that are not tied to a tool call are serialized into span attributes without applying redaction. Their content, which can quote invalid values from the model's response, reaches the telemetry backend even when content collection is disabled. The fix applies the include_content check to retry prompt parts like all other message content.
Who does this affect?
You are affected if you are using a version that falls within the vulnerable range and you enable OpenTelemetry instrumentation with include_content=False.
Background info
pydantic-ai-slim is vulnerable to Exposure of Sensitive Information in versions 0.3.4 - 1.107.2 and 2.0.0 - 2.27.0.
How to fix this
Upgrade the pydantic-ai-slim and/or the pydantic-ai library to the patch version.
Are You Affected?
Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.
Free. No credit card required.
I consent to receiving marketing communications based on Aikido’s Privacy Policy.
SOC 2Compliant
ISO 27001Compliant