The rapid use of generative AI tools has greatly improved productivity for developers and organizations. However, it also poses serious security risks, particularly the accidental exposure of sensitive data and the inclusion of potentially malicious code from outside sources. This paper introduces Yuno AI, a secure pre-prompt framework that examines user inputs before generative AI systems process them. The system identifies sensitive information, such as personal identifiers, credentials, and confidential project details, through pattern- based analysis and natural language processing. Additionally, Yuno AI includes a code security analysis module that checks externally sourced or AI-generated code for suspicious patterns, such as hidden network requests, telemetry scripts, access to environment variables, and other signs of supply-chain attacks. The system assigns a risk score and automatically cleans or adjusts unsafe inputs before sending them to AI models. By serving as a security layer between users and AI systems, Yuno AI helps create safer and more reliable AI-assisted development environments.

This article introduced Yuno AI, a proactive security framework that aims to stop the leakage of sensitive data in the course of using generative AI systems. The method put forward a pre-prompt interception feature that examines the users’ inputs before sending them to the external AI platforms, which makes it possible to recognize the exposition of sensitive information such as personal data, API keys, and secret project details. The incorporation of a variety of detection strategies, semantic analysis, risk scoring, and anonymization techniques that preserve context is what allows Yuno AI to safeguard sensitive data and at the same time keep AI tools usable. Furthermore, the framework features modules for idea intelligence and code security analysis that can help with innovation and also identify software supply chain risks. The results of the experiment show that the system can detect with very high accuracy while at the same time, it takes a very short time to process, which makes it a good fit for real-time scenarios. In general, Yuno AI is a timely and effective approach to the problem of data leakage caused by Shadow AI, and it is also a step towards the secure and responsible use of AI technologies in our digitally interconnected world

[1]Jadhav, P. and Chawan, P., 2019. Data leak prevention system: A survey. Virus, 6(10), pp.197–199. [2]Ahmad, M.S. and Bamnote, G.R., 2013. Data leakage detection and data prevention using algorithm. International Journal Of Computer Science And Applications, 6(2), pp.394-399. [3]Kaur, K., Gupta, I. and Singh, A.K., 2017, August. A comparative evaluation of data leakage/loss prevention systems (DLPS). In Proc. 4th Int. Conf. Computer Science & Information Technology (CS & IT-CSCP) (pp. 87-95). [4]Rossi, M.C., 2023. Enhancing cyber assets visibility for effective attack surface management. [5]Ahmad, S., Mehfuz, S., Mebarek-Oudina, F. and Beg, J., 2022. RSM analysis based cloud access security broker: a systematic literature review. Cluster computing, 25(5), pp.3733-3763. [6]Hauer, B., 2014, April. Data leakage prevention. In SciTePress (Vol. 2, pp. 361-367). [7]Kulkarni, P. and Cauvery, N.K., 2021. Personally identifiable information (pii) detection in the unstructured large text corpus using natural language processing and unsupervised learning technique. International Journal of Advanced Computer Science and Applications, 12(9). [8] Puthal, D., Mishra, A.K., Mohanty, S.P., Longo, A. and Yeun, C.Y., 2025. Shadow AI: Cyber Security Implications, Opportunities and Challenges in the Unseen Frontier. SN Computer Science, 6(5), p. 405. [9]Esther, D., AI in Data Loss Prevention: Safeguarding Sensitive Data Against Unauthorized Access and Leakage. [10Purohit, B. and Singh, P.P., 2013. Data leakage analysis on cloud computing. International Journal of Engineering Research and Applications, 3(3), pp.1311-1316. [11]Mainetti, L. and Elia, A., 2025. Detecting Personally Identifiable Information Through Natural Language Processing: A Step Forward. Applied System Innovation, 8(2), p.55. [12]Ahmad, M.S. and Bamnote, G.R., 2013. Data leakage detection and data prevention using algorithm. International Journal Of Computer Science And Applications, 6(2), pp.394-399. [13]Kulkarni, P. and Cauvery, N.K., 2021. Personally identifiable information (pii) detection in the unstructured large text corpus using natural language processing and unsupervised learning technique. International Journal of Advanced Computer Science and Applications, 12(9). [14]Dong, M., Yakura, H., Sherif, O., Bonnefon, J.F. and Rahwan, I., 2025. Shadow AI thrives under punitive social evaluation. [15]Puthal, D., Mishra, A.K., Mohanty, S.P., Longo, A. and Yeun, C.Y., 2025. Shadow AI: Cyber Security Implications, Opportunities and Challenges in the Unseen Frontier. SN Computer Science, 6(5), p.405

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close