Climate and Earth system models are important tools to assess the benefits and risks of stratospheric aerosol injection (SAI) relative to those associated with anthropogenic climate change. A “controller” algorithm has been used to specify injection amounts of sulfur dioxide in SAI experiments performed with the Community Earth System Model (CESM). The experiments are designed to maintain specific temperature targets, such as limiting global mean temperature to 1.5ºC above the pre-industrial level. However, the influence of natural climate variability on the injection amount has not been extensively documented. Our study reveals that more than 70% of the year-to-year variation in the total injection amount (excluding the long-term trend) in CESM SAI experiments is attributed to the El Niño-Southern Oscillation (ENSO). A simplified statistical model further suggests that the intrinsic, lagged response of the controller to the climate can increase the variance of global mean temperature in the model simulations.