MicroRNAs (miRNAs) have been extensively studied as non-invasive biomarkers for cancer diagnosis and prognosis, while the clinical application was constrained by the heterogeneous miRNA sources in plasma and the tedious assay processes. Here we developed a one-pot assay called dual-Surface-protein-guided Orthogonal Recognition of Tumor-derived Exosomes and in-situ profiling of microRNAs (SORTER) for rapid and precise diagnosis of prostate cancer. The SORTER utilizes the orthogonal barcoding of two allosteric aptamers against exosomal marker CD63 and tumor marker EpCAM to recognize and sort tumor-derived exosome subtypes. Furthermore, the labeled barcode on tumor-derived exosomes guided the targeted fusion with liposome miRNA detection probes, enabling in-situ profiling of tumor-derived exosomal miRNAs. With a signature of six miRNAs, SORTER differentiated prostate cancer and benign prostatic hyperplasia with a sensitivity, specificity, and accuracy of 100% in the training and validation cohorts. The SORTER provides a promising tool to advance the clinical adaptability of miRNA-based liquid biopsy.