THREATOPS
THREAT OPS › Threat News › [GHSA] GHSA-3gh4-cghq-f8v4 (low) — Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`

[GHSA] GHSA-3gh4-cghq-f8v4 (low) — Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`

medgithub_advisoriesPublished 2026-10-08

GHSA-3gh4-cghq-f8v4 Severity: low CVE: CVE-2026-107293

Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`

### Summary

Pydantic AI's OpenTelemetry instrumentation supports `InstrumentationSettings(include_content=False)` to exclude message content — user prompts, model completions, tool call arguments and responses — from exported telemet

Indicators of compromise

Original source: https://github.com/advisories/GHSA-3gh4-cghq-f8v4