red-run — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 blacklanternsecurity · Claude Skill · ★ 253

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is red-run safe to install? View the security audit →

About red-run

red-run Security assessment toolkit for Claude Code. red-run combines skills, MCP servers, and Claude Code agent teams with routing logic that guides Claude and the operator through the phases of a security assessment — recon, initial access, lateral movement, privilege escalation, and post-access. It tracks engagement state in a SQLite database that persists across context compactions, routes to skills via semantic search (RAG), and delegates execution to persistent domain teammates that accumulate context across tasks. The orchestrator (team lead) presents the assessment surface, chain analysis, and available paths — you choose what to test next. Teammates work in their own tmux panes where you can watch them, press Escape to interrupt, and type directly to redirect. See Agent Teams below for setup. Orchestrators red-run supports multiple orchestrator variants that share the same skills, MCP servers, and engagement state. Each variant targets a different use case. Community contributions welcome. /red-run

claudeclaude-codectfoffensive-securitypenetration-testingred-teamsecurity

Quick Facts

Stars253
Forks37
LanguagePython
CategoryClaude Skill
LicenseGPL-3.0
Quality Score70.295607527367/100
Open Issues4
Last Updated2026-04-01
Created2026-02-22
Platformsclaude-code, python
Est. Tokens~548k

red-run alternative? Top 6 similar tools

Looking for a red-run alternative? If you're comparing red-run with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • h5i by h5i-dev · ⭐ 652

    An agent-native red-teaming workspace with a fast browser, direct HTTP traffic control, sandboxed execution, a

  • tengu by rfunix · ⭐ 58

    AI-powered penetration testing MCP server

  • perseus by kaivyy · ⭐ 67

    AI-powered security assessment SKILLS for your codebase. Multi-language (JS, Go, Python, Rust, Java, PHP, Ruby

  • mcp-security-hub by FuzzingLabs · ⭐ 758

    A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei,

  • code-on-incus by mensfeld · ⭐ 728

    Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops t

  • vestige by samvallad33 · ⭐ 628

    Cognitive Deterministic Memory Security OS for Agentic AI. Deterministic root-cause retrieval that reaches bac

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is red-run?

red-run is Offensive security toolkit for Claude Code. It is categorized as a Claude Skill with 253 GitHub stars.

What programming language is red-run written in?

red-run is primarily written in Python. It covers topics such as claude, claude-code, ctf.

How do I install or use red-run?

You can find installation instructions and usage details in the red-run GitHub repository at github.com/blacklanternsecurity/red-run. The project has 253 stars and 37 forks, indicating an active community.

What license does red-run use?

red-run is released under the GPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to red-run?

The top alternatives to red-run on Agent Skills Hub include h5i, tengu, perseus. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Claude Skill tools