Forensic genetics is moving from locus-based DNA profiling toward genome-wide inference enabled by high-density single-nucleotide polymorphism (SNP) data. While short tandem repeats remain central to routine human identification, SNP-based technologies and massively parallel sequencing have expanded the analysis of distant kinship through detection of identity-by-descent (IBD) segments and shared autosomal DNA. This narrative review synthesizes the biological basis of SNP-based distant kinship inference, the statistical and computational frameworks used to model genomic relatedness, and the operational transition from relatedness detection to forensic genetic genealogy (FGG). It distinguishes genetic genealogy database matching from formal forensic kinship testing, targeted SNP panels, SNP capture, low-coverage sequencing, Bayesian and machine-learning approaches, and independent forensic confirmation. Applications in criminal investigations, unidentified human remains, historical identifications, and broader relationship-inference contexts are discussed. The review also examines limitations related to recombination, stochastic inheritance, marker density, genotype quality, degraded or mixed forensic samples, population structure, endogamy, database composition, and genealogical record availability. Ethical and regulatory issues involving consent, privacy, database governance, law-enforcement access, data retention, and non-consenting relatives are considered. Overall, SNP-based forensic genomics can generate powerful investigative leads, but its outputs must be interpreted within method-specific analytical and evidentiary boundaries.