Incident database

MLflow CrewAI autologging leaks LLM API keys in trace spans

MLflow's CrewAI autologging feature automatically records LLM provider API keys in plaintext within trace span attributes and inputs. The vulnerability occurs through two independent serialization paths that convert credential-bearing objects to strings without sanitization.

Disclosed 27 October 2026 · Record updated 28 October 2026

Our coverage

Vulnerabilities

MLflow autologging writes CrewAI API keys into trace data

A GitHub advisory published on 27 October 2026 says MLflow's CrewAI integration copies LLM provider API keys into trace spans in plaintext.

28 Oct 2026