Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
nullsec-s1
Security-native LLM system for AI-generated application security.
169stars
52forks
Python
ai-securityappseccode-securityllmmcpqlorasecurityvibecodingweb3-security
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
AI-powered security scanner that flags vulnerabilities in code using a security-native large language model.
Use this when
- reviewing pull requests for security flaws
- auditing legacy code for known vulnerabilities
- checking third-party dependencies for supply-chain risks
- compliance checks for security standards like OWASP
- onboarding new developers to security best practices
Don't use when
- scanning non-code assets like binaries or containers
- performing deep manual penetration testing
- analyzing runtime behavior or network traffic
Capabilities
- detects OWASP Top 10 vulnerabilities in source code
- flags hardcoded secrets like API keys or passwords
- identifies outdated or vulnerable dependencies
- provides severity scores for found issues
- integrates with CI/CD pipelines via CLI or API
- supports multiple languages including Python, JavaScript, Java
InstallMCPRun via uvx (Python)
Universal installANY TOOL
$ npx skillcity@latest trynullsec/nullsec-s1Auto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
uvx nullsec-s1
MCP Configuration
Add this to your claude_desktop_config.json
{
"mcpServers": {
"nullsec-s1": {
"command": "uvx",
"args": [
"nullsec-s1"
]
}
}
}Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
nullsec-s1 — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt