The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers across function-level, repository-level, agentic, and smart-contract detection, plus datasets, benchmarks, and surveys.
Prevent merging of malicious code in pull requests
Django application that performs SAST and Malware Analysis for Android APKs
Redefining vulnerability disclosure in the AI era. We mass-produce exploitable 0days and disclose them directly, using event-driven pressure to elevate vendor security standards and advance the field.
Focused malicious code detection ruleset, with a high protection-to-noise ratio
AI-powered SAST scanner that finds auth bypass, IDOR, and logic bugs Semgrep/CodeQL miss. Free GitHub Action. Supports Python, JS/TS, Go, PHP, Ruby.
Open-source AI verification infrastructure for deterministic verification of LLM outputs, tool calls, code, schemas, and agent state before production execution.
OpenVul: An Open-Source Post-Training Framework for LLM-Based Vulnerability Detection
Codeaudit - Modern Python source code security analyzer based on distrust.
Detect and patch vulnerabilities in AI-generated Python code — VS Code extension
AI code generation and improvement
NEXUS REDFOX — Local-first code intelligence and security analysis platform for developers and security researchers.
GoBfuscator is a professional-grade obfuscation tool specifically designed for Go (Golang) source code. It provides multiple layers of protection to make reverse engineering difficult while maintaining 100% runtime functionality.
Contexi let you interact with entire codebase or data with context using a local LLM on your system.
Adversarial AI Coding: Self-Play Sparring, Offense Meets Defense — Making AI Write Secure Code
Secure-coding gates for AI-written code — 67 gates across 13 OWASP-aligned topics, checked before code ships.
🔍 CodeVista — AI-powered code analysis & visualization tool. Understand complex codebases instantly. Dependency graphs, architecture insights & quality metrics.
White-box AI code security review for Claude/Codex: offline scanner, review packs, SARIF, and report merging.
Universal security scanning skill for AI agents - finds hardcoded secrets, API keys, and vulnerabilities in any codebase. 60 regex rules (46 GitLeaks-informed secret patterns, 14 OWASP Top 10 checks) plus 15 dangerous-file checks. Markdown/SARIF/JSON reports. Works across Claude Code, Cursor, Windsurf, and any agentic platform.
Scan code for invisible bidirectional Unicode characters (Trojan Source attack prevention, CVE-2021-42574)
To associate your repository with the code-security topic, visit your repo's landing page and select "manage topics."