Androgen deprivation therapy (ADT) has been hypothesized to protect against COVID‐19, but previous observational studies of men with prostate cancer on ADT have been inconsistent regarding mortality risk from coronavirus disease 2019 (COVID‐19). Using data from the Prostate Cancer data Base Sweden (PCBaSe), we identified a cohort of 114 547 men with prevalent prostate cancer on the start of follow‐up in February 2020, and followed them until 16 December 2020 to evaluate the association between ADT and time to test positive for COVID‐19. Among men testing positive for COVID‐19, we used regression analyses to estimate the association between ADT and risk of COVID‐19‐related hospital admission/death from any cause within 30 days of the positive test. In total, 1695 men with prostate cancer tested positive for COVID‐19. In crude analyses, exposure to ADT was associated with a 3‐fold increased risk of both testing positive for COVID‐19 infection and subsequent hospital admission/death. Adjustment for age, comorbidity and prostate cancer risk category substantially attenuated the associations: HR 1.3 (95% CI: 1.1‐1.5) for testing positive for COVID‐19, and OR 1.4 (95% CI: 1.0‐1.9) for risk of subsequent hospital admission/death. In conclusion, although these results suggest increased risks of a positive COVID‐19 test, and COVID‐19‐related hospital admission/death in men on ADT, these findings are likely explained by confounding by old age, cancer‐associated morbidity and other comorbidities being more prevalent in men on ADT, rather than a direct effect of the therapy.