VibeGuard: A Security Gate Framework for AI-Generated Code

• URL: http://arxiv.org/abs/2604.01052v1
• Date: Wed, 01 Apr 2026 15:57:01 GMT
• Title: VibeGuard: A Security Gate Framework for AI-Generated Code
• Abstract summary: Anthropic's Claude Code CLI shipped a 59.8 MB source map file in its npm package exposing 512,000 lines of proprietary TypeScript.<n>We present VibeGuard, a pre-publish security gate that targets five such blind spots.<n>We discuss how these results inform a defense-in-depth workflow for teams that rely on AI code generation.
• Score: 0.11080037957254413
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: "Vibe coding," in which developers delegate code generation to AI assistants and accept the output with little manual review, has gained rapid adoption in production settings. On March 31, 2026, Anthropic's Claude Code CLI shipped a 59.8 MB source map file in its npm package, exposing roughly 512,000 lines of proprietary TypeScript. The tool had itself been largely vibe-coded, and the leak traced to a misconfigured packaging rule rather than a logic bug. Existing static-analysis and secret-scanning tools did not cover this failure mode, pointing to a gap between the vulnerabilities AI tends to introduce and the vulnerabilities current tooling is built to find. We present VibeGuard, a pre-publish security gate that targets five such blind spots: artifact hygiene, packaging-configuration drift, source-map exposure, hardcoded secrets, and supply-chain risk. In controlled experiments on eight synthetic projects (seven vulnerable, one clean control), VibeGuard achieved 100% recall, 89.47% precision (F1 = 94.44%), and correct pass/fail gate decisions on all eight projects across three policy levels. We discuss how these results inform a defense-in-depth workflow for teams that rely on AI code generation.

Related papers

• Towards a Risk Assessment of Malicious Skill Files in Coding Agents [9.553517006800913]
  We make three contributions to the field of autonomous coding agents.<n>First, an adversarial skill-synthesis method to transform 471 real-world shell commands into benign-appearing skills.<n>Second, a reproducible evaluation pipeline coupling run stratification, evidence anchoring, a refusal veto, and a deterministic declared-intent override.<n>Third, a large-scale characterization of two enterprise-grade agents across 5,629 completed runs.
  arXiv  Detail & Related papers  (2026-08-05T11:33:43Z)
• Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens [65.53494487819053]
  Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services.<n>We adopt a computer-system analogy: treating a Claw-like agent as an agentic computer system whose gateway runtime plays an OS-like mediation role.<n>We develop SafeClawArena, a benchmark of 406 adversarial tasks across four attack surfaces.
  arXiv  Detail & Related papers  (2026-06-29T18:00:45Z)
• ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks? [92.21756459993695]
  Exploitation is a challenging task because it requires low-level program reasoning.<n>Despite its importance and diagnostic value, exploitation remains under-evaluated.<n>We introduce ExploitGym, a large-scale, diverse, realistic benchmark on the exploitation capabilities of AI agents.
  arXiv  Detail & Related papers  (2026-05-11T18:00:14Z)
• AegisUI: Behavioral Anomaly Detection for Structured User Interface Protocols in AI Agent Systems [0.0]
  Current defenses stop at syntax; they were never built to catch this kind of behavioral mismatch.<n>AegisUI generates structured UI payloads, injects realistic attacks into them, extracts numeric features, and benchmarks anomaly detectors end-to-end.<n>We produced 4000 labeled payloads spanning five application domains and five attack families.
  arXiv  Detail & Related papers  (2026-03-05T10:24:43Z)
• Security Vulnerabilities in AI-Generated Code: A Large-Scale Analysis of Public GitHub Repositories [0.0]
  This paper presents a comprehensive empirical analysis of security vulnerabilities in AI-generated code across public GitHub repositories.<n>We collected and analyzed 7,703 files explicitly attributed to four major AI tools: ChatGPT, GitHub Copilot, Amazon CodeWhisperer, and Tabnine.<n>Using CodeQL static analysis, we identified 4,241 Common Weaknession (CWE) instances across 77 distinct vulnerability types.
  arXiv  Detail & Related papers  (2025-10-30T03:29:06Z)
• Trace: Securing Smart Contract Repository Against Access Control Vulnerability [58.02691083789239]
  GitHub hosts numerous smart contract repositories containing source code, documentation, and configuration files.<n>Third-party developers often reference, reuse, or fork code from these repositories during custom development.<n>Existing tools for detecting smart contract vulnerabilities are limited in their ability to handle complex repositories.
  arXiv  Detail & Related papers  (2025-10-22T05:18:28Z)
• Decompiling Smart Contracts with a Large Language Model [51.49197239479266]
  Despite Etherscan's 78,047,845 smart contracts deployed on (as of May 26, 2025), a mere 767,520 ( 1%) are open source.<n>This opacity necessitates the automated semantic analysis of on-chain smart contract bytecode.<n>We introduce a pioneering decompilation pipeline that transforms bytecode into human-readable and semantically faithful Solidity code.
  arXiv  Detail & Related papers  (2025-06-24T13:42:59Z)
• BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems [62.17474934536671]
  We introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems.<n>To capture the vulnerability lifecycle, we define three task types: Detect (detecting a new vulnerability), Exploit (exploiting a specific vulnerability), and Patch (patching a specific vulnerability)<n>We evaluate 8 agents: Claude Code, OpenAI Codex CLI with o3-high and o4-mini, and custom agents with o3-high, GPT-4.1, Gemini 2.5 Pro Preview, Claude 3.7 Sonnet Thinking, and DeepSeek-R1.
  arXiv  Detail & Related papers  (2025-05-21T07:44:52Z)
• ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs [56.46702494338318]
  This paper introduces a new attack paradigm: (automatic) external prompt injection against code-oriented large language models.<n>We propose ShadowCode, a simple yet effective method that automatically generates induced perturbations based on code simulation.<n>We evaluate our method across 13 distinct malicious objectives, generating 31 threat cases spanning three popular programming languages.
  arXiv  Detail & Related papers  (2024-07-12T10:59:32Z)
• FV8: A Forced Execution JavaScript Engine for Detecting Evasive Techniques [53.288368877654705]
  FV8 is a modified V8 JavaScript engine designed to identify evasion techniques in JavaScript code. It selectively enforces code execution on APIs that conditionally inject dynamic code. It identifies 1,443 npm packages and 164 (82%) extensions containing at least one type of evasion.
  arXiv  Detail & Related papers  (2024-05-21T19:54:19Z)
• Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study [8.364612094301071]
  We analyze code snippets generated by GitHub Copilot and two other AI code generation tools from GitHub projects.<n>Our analysis identified 733 snippets, revealing a high likelihood of security weaknesses, with 29.5% of Python and 24.2% of JavaScript snippets affected.<n>We provide suggestions for mitigating security issues in generated code.
  arXiv  Detail & Related papers  (2023-10-03T14:01:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.