TY  - EJOU
AU  - Akasam, Bala Thripura 

TI  - Shift-Left Security for AI-Generated Code: Detecting and Preventing Vulnerabilities at Build-Time
T2  - Journal of Cyber Security

PY  - 2026
VL  - 8
IS  - 1
SN  - 2579-0064

AB  - The widespread adoption of Artificial Intelligence (AI) coding assistants across enterprise software development teams has accelerated delivery velocity while simultaneously introducing a persistent and empirically documented security quality gap in the code these tools produce. Vulnerability classes including insecure output handling, prompt injection constructs, sensitive information disclosure patterns, and cryptographic misuse appear at elevated rates in AI-generated output regardless of model advancement, while organizational governance frameworks have failed to keep pace with the speed of AI tool deployment, creating conditions in which vulnerable code reaches production through informal risk acceptance rather than accountable remediation processes. The conventional shift-left security practice of running static application security testing earlier in the Continuous Integration pipeline (CI pipeline) is insufficient to address these conditions, as AI-amplified code volumes overwhelm static analysis triage capacity and produce finding sets that lack the runtime exploitability context needed to distinguish genuine risk from theoretical noise. This article develops a structured, research-backed blueprint for build-time security controls tailored specifically to AI-generated code, organized across three interdependent layers: a pre-pull-request policy and governance layer; a build-time detection layer combining AI-augmented and traditional static analysis, Application Programming Interface (API) schema validation, automated Software Bill of Materials (SBOM) enforcement, and pre-deployment runtime simulation; and a prioritization and feedback layer applying application security posture management correlation to convert detection volume into developer-actionable risk reduction. An evaluation framework centered on precision and recall per vulnerability class, True-Exploit Rate, mean time to remediate, supply-chain integrity coverage, and developer experience indicators provides the measurement infrastructure needed to demonstrate risk reduction outcomes rather than detection counts.
KW  - Shift-left security; AI-generated code vulnerabilities; software bill of materials; application security posture management; DevSecOps build-time controls

DO  - 10.32604/jcs.2026.085438