Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-116691— MLflow CrewAI autologging records LLM provider API keys in logged trace spans

Quick assessment

Affected
mlflow mlflow
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

MLflow 是一个面向智能体（Agents）、大型语言模型和机器学习模型的开源 AI 工程平台。在版本 2.19.0 至 3.17.0 期间， 在记录 CrewAI 智能体对象时，未能始终对嵌套的含凭证值进行一致化清理。具体而言， 会将智能体的 字段转换为字符串，该字符串中包含了提供商的 API 密钥；而 则会将智能体对象展开为 。因此，应用程序可能将明文形式的提供商凭证发送至 MLflow 追踪后端或已配置的 OTLP（OpenTelemetry Protocol）目的地，使得追踪数据的读取者能够获取这些凭证。

CVSS 6.5 · Medium
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-116691

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
MLflow CrewAI autologging records LLM provider API keys in logged trace spans
Source: CVE Program / CVE List V5
Vulnerability Description
MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 2.19.0 until 3.17.0, mlflow.crewai.autolog() records CrewAI Agent objects without consistently sanitizing nested credential-bearing values. mlflow/crewai/autolog.py::_get_agent_attributes() converts the Agent llm field to a string that includes the provider API key, while mlflow/crewai/autolog.py::_construct_full_inputs() expands the Agent object into mlflow.spanInputs. Applications can therefore send plaintext provider credentials to the MLflow trace backend or a configured OTLP destination, where trace readers can obtain them. This issue is fixed in version 3.17.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
信息暴露
Source: CVE Program / CVE List V5

Affected Products

Vendor Product Affected Versions CPE Subscribe
mlflow mlflow >= 2.19.0, < 3.17.0 -

II. Public POCs for CVE-2026-116691

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-116691

请登录查看更多情报信息。

Vendor Pages for CVE-2026-116691 (1)

Other References for CVE-2026-116691 (3)

Same Patch Batch · mlflow · 2026-10-27 · 3 CVEs total

CVE-2026-116692 9.8 CRITICAL MLflow: Remote code execution on unauthenticated MLflow servers via third-party scorer des
CVE-2026-116690 7.5 HIGH MLflow: Arbitrary file read on unauthenticated MLflow servers via prompt model version sou

IV. Related Vulnerabilities

Same product: mlflow
Same vendor: mlflow
Same weakness: CWE-200