Objective To systematically evaluate the studies on existing risk prediction models for surgical site infection (SSI) in patients with colorectal cancer (CRC). Methods Relevant studies on SSI prediction models for CRC patients were retrieved from PubMed, Embase, Web of Science, Cochrane Library, China National Knowledge Infrastructure (CNKI), VIP, and Wanfang. The retrieval period was from the establishment dates of the databases to April 2025. Two researchers independently conducted literature screening and information extraction, and evaluated the risk of bias in the literatures using PROBAST tool. Results A total of 25 literatures were included in the analysis, and the incidences of SSI were 4.35%-29.47%, including 35 risk prediction models of SSI following CRC surgery. The areas under the curve (AUCs) of the receiver operating characteristic (ROC) of models were all >0.7. 12 studies underwent internal validation and 4 studies underwent internal and external validation. The final number of included predictors was 2-13. Diabetes, duration of operation, operation mode, preoperative hypoproteinemia, body mass index (BMI), and age were high frequency predictors. All studies were evaluated as with risk of high bias, while 14 studies were evaluated as with risk of low applicability. Conclusion The overall predictive performance of existing prediction models for SSI following CRC surgery is good, however, there are limitations such as insufficient sample size and lack of external validation, and the quality of models needs to be improved. Future model development should strictly follow the PROBAST standard, strengthen the design of prospective and multicenter study with large sample size, attach importance to and standardize external validation processes, scientific processing, and data reporting, so as to improve model quality and clinical applicability value. In clinical practice, special attention should be paid to patients with high-frequency risk factors, and targeted intervention measures should be taken to reduce the risk of SSI occurrence.