No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Armur-Ai · Agent Tool · ★ 84
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is vibescan safe to install? View the security audit →
vibescan Security Scanner for Vibe-Coded Software Scan AI-generated code for vulnerabilities before they ship. Quick Start • Interactive TUI • Features • Languages • CLI Reference • CI/CD • MCP • Contributing Credits & Inspiration vibescan stands on the shoulders of incredible open-source security projects. We didn't reinvent the wheel — we built an orchestration layer that unifies the best tools into a single, developer-friendly experience. Projects that inspired us: Comprehe
| Stars | 84 |
| Forks | 15 |
| Language | Go |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67.9851058548822/100 |
| Last Updated | 2026-09-30 |
| Created | 2024-12-13 |
| Platforms | go |
| Est. Tokens | ~20k |
Looking for a vibescan alternative? If you're comparing vibescan with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Security operations toolkit for AI coding agents. Give Claude Code 25+ skills to catch vulnerabilities, scan c
Open-source cybersecurity analysis agent for Claude Code. Scans projects for vulnerabilities across all OWASP
The open source taint analysis engine for the AI era. A formal dataflow analysis tool you can customize and se
Static Code Analysis for security teams with Inter file taint analysis. Built for finding vulnerabilities, adv
Production-grade MCP server for Wazuh SIEM — 55 security tools for alert triage, threat hunting, vulnerability
AI-powered cybersecurity code review skill for Claude Code. 8 specialist agents, OWASP 2025, CWE Top 25, MITRE
Explore other popular agent tool tools:
vibescan is Security scanner for AI-generated ("vibe-coded") code. Runs SAST, DAST, and sandboxed exploit simulation across 15+ languages using 30+ tools. Catches what LLMs introduce before it ships — wit. It is categorized as a Agent Tool with 84 GitHub stars.
vibescan is primarily written in Go. It covers topics such as code-scanning, dast, devsecops.
You can find installation instructions and usage details in the vibescan GitHub repository at github.com/Armur-Ai/vibescan. The project has 84 stars and 15 forks, indicating an active community.
vibescan is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to vibescan on Agent Skills Hub include SecOpsAgentKit, cyber-neo, opentaint. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: