MLflow CrewAI autologging records LLM provider API keys in logged trace spans

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

6.5 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

EPSS

• CVE-2026-116691: 0.21% estimated exploitation activity in the next 30 days; percentile 10.88 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary `mlflow.crewai.autolog()` leaks CrewAI LLM provider API keys into MLflow trace telemetry. When a CrewAI `Agent` is instrumented with MLflow autologging, MLflow serializes the agent's `dict` and converts its fields to strings. The `llm` field contains the CrewAI LLM object, whose string representation includes its `api_key` in plaintext. As a result, an application that calls `mlflow.crewai.autolog()` can unintentionally send its LLM provider API key to the MLflow trace backend or configured OTLP destination. The application does not need to explicitly log the credential or place it in a span attribute. The credential is extracted automatically by MLflow's instrumentation. This was verified on MLflow 3.16.0 with CrewAI 1.15.18 using MLflow's own OTLP exporter. The fake credential appeared in 5 attribute locations across 2 spans.

Details The primary issue is in: `mlflow/crewai/autolog.py::_get_agent_attributes()` The function walks the CrewAI…

Published by the source

27 Oct 2026, 21:26 UTC

Last modified by the source

27 Oct 2026, 21:45 UTC

Source last checked

28 Oct 2026, 06:05 UTC

1. Revision 2 · amended · 28 Oct 2026

   Amended from osv record GHSA-j7qq-vr8c-xvw3

2. Revision 1 · created · 27 Oct 2026

   Published from ghsa record GHSA-j7qq-vr8c-xvw3

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-116691

Advisory: MLflow CrewAI autologging records LLM provider API keys in logged trace spans
IDs: CVE-2026-116691, GHSA-j7qq-vr8c-xvw3
Record: https://patchnext.com/advisories/cve-2026-116691 (revision 2, source checked 28 Oct 2026, 06:05 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Medium (CVSS 6.5)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: mlflow 3.17.0. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI mlflow: affected >= 2.19.0, < 3.17.0; fixed in 3.17.0

## Suggested inspection (read-only)
- `python -m pip show mlflow`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on mlflow.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-j7qq-vr8c-xvw3 (OSV record GHSA-j7qq-vr8c-xvw3 lists affected ranges: PyPI mlflow >=2.19.0 <3.17.0 (fixed))
- Verified: https://github.com/advisories/GHSA-j7qq-vr8c-xvw3 (GitHub-reviewed advisory GHSA-j7qq-vr8c-xvw3 lists affected ranges: PyPI mlflow >=2.19.0 <3.17.0)

Commands are suggestions: review each one before running it.