PolicyGuard: Prompt-Configurable Semantic DLP for LLM Coding Agents

Computer Science > Cryptography and Security [Submitted on 3 Aug 2026] PolicyGuard: Prompt-Configurable Semantic DLP for LLM Coding Agents Kyutae Park, Jungwon Kim, Daeyeol Shim AI coding agents accept free-form natural language prompts that may inadvertently contain credentials, personally identifiable information (PII), or proprietary business data. Existing data loss prevention (DLP) solutions rely on rigid regex patterns, model fine-tuning, or vendor-managed classifiers with limited customizability. We present PolicyGuard, a pre-model interception framework that classifies user prompts using an LLM guided by a natural language policy file. Our key contributions are: (1) the policy-as-prompt paradigm, where DLP classification criteria are defined entirely in a plaintext policy document editable by non-engineers without code changes or model retraining; (2) a sealed evaluation protocol with template-family-level data splits, hidden holdouts, and frozen test sets to rigorously assess generalization; and (3) a comprehensive empirical evaluation across 2,000 multilingual prompts demonstrating 96.5% effective block rate (EBR) with only 3.0% false positive rate (FPR) on a frozen test set of 927 prompts, and perfect 100% accuracy on a 217-prompt hidden holdout. Information-matched baseline experiments show that PolicyGuard's natural language format significantly outperforms equivalent content in JSON format (McNemar chi-squared = 31.58, p < 0.001) and dramatically outperforms zero-shot classification (Cohen's h = 0.915). Cross-model portability experiments demonstrate that the same policy achieves 86.4-96.5% EBR across four different LLMs without modification. Comments: 10 pages, 5 figures, 8 tables Subjects: Cryptography and Security (cs.CR); Software Engineering (cs.SE) Cite as: arXiv:2608.02687 [cs.CR]   (or arXiv:2608.02687v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.02687 Focus to learn more Submission history From: Kyutae Park [view email] [v1] Mon, 3 Aug 2026 08:10:15 UTC (58 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-08 Change to browse by: cs cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)