PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-107293 pydantic CVE debrief

Pydantic AI's OpenTelemetry instrumentation supports `InstrumentationSettings(include_content=False)` to exclude message content from exported telemetry. However, retry prompts were not covered by this setting when they were not associated with a tool call, potentially allowing sensitive content to reach the telemetry backend. This oversight could impact defenders who rely on this setting to protect sensitive information. To address this, defenders should review their current configuration and ensure that it aligns with their security requirements. They should also verify that the instrumentation is properly set up to exclude sensitive content from telemetry.

Vendor
pydantic
Product
pydantic-ai
CVSS
LOW 2.3
CISA KEV
Not listed in stored evidence
Original CVE published
2026-10-08
Original CVE updated
2026-10-08
Advisory published
2026-10-08
Advisory updated
2026-10-08

Who should care

Defenders responsible for configuring and monitoring Pydantic AI's OpenTelemetry instrumentation should assess exposure and verify the configuration to ensure sensitive content is properly excluded from telemetry.

Why it matters

Defenders should prioritize verifying the configuration of Pydantic AI's OpenTelemetry instrumentation and ensuring that sensitive content is properly excluded from telemetry to prevent potential exposure.

  • Potential exposure of sensitive content in telemetry
  • Verification priority for Pydantic AI's OpenTelemetry instrumentation configuration
  • Defensive priority for ensuring proper exclusion of sensitive content

Technical summary

Pydantic AI's OpenTelemetry instrumentation does not redact retry prompt content when `include_content=False`. This could allow sensitive content to be included in telemetry. The issue arises from retry prompts not being covered by the `include_content=False` setting when they are not associated with tool calls. This setting is intended to exclude message content from exported telemetry, but the oversight in handling retry prompts could lead to unintended exposure of sensitive information. Defenders should prioritize verifying the configuration of Pydantic AI's OpenTelemetry instrumentation and ensuring that sensitive content is properly excluded from telemetry.

Defensive priority

Defenders should prioritize verifying the configuration of Pydantic AI's OpenTelemetry instrumentation and ensuring that sensitive content is properly excluded from telemetry.

Recommended defensive actions

  • Verify the configuration of Pydantic AI's OpenTelemetry instrumentation
  • Ensure that sensitive content is properly excluded from telemetry
  • Monitor for potential exposure in affected versions
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up

Evidence notes

The CVE record and source item provide details on the vulnerability, including the affected versions and configurations. However, the corpus does not establish versions, exploitation, impact, or remediation with certainty.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-107293 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-107293

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-107293 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-107293

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

  • Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_co

    Unverified legacy reference

    URL: https://storage.googleapis.com/osv-vulnerabilities/PyPI/GHSA-3gh4-cghq-f8v4.json

    osv_dev

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-3gh4-cghq-f8v4

    Supplemental source

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/pull/7357

    Supplemental source

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/commit/fe9dbed7b7ccf7e7128b5786886e4441f6f5594f

    Supplemental source

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai

    Supplemental source

  • Source reference

    Unverified legacy reference

    URL: https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1

    Supplemental source

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.