BurnyCoder

Security Monitoring Agent — Security skill for Claude Code

Security community

How to install Security Monitoring Agent

This entry records only its repository, not the path inside it, so there is no exact command to give. Open BurnyCoder/security-monitoring-agent and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Security Monitoring Agent does

Windows + WSL vulnerability and exploits monitoring dashboard that combines observed software inventory, CISA known-exploitation intelligence, OSV dependency checks, and live web research by Codex or Claude Code. Findings explain which installation an advisory may affect, cite the evidence, and propose fixes to inspect and copy.

Alternatives in Security

Token Scan — Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP l 3.8k ★
Cve MCP Server — Production-grade MCP server giving Claude 27 security intelligence tools across 21 APIs — CVE lookup, EPSS sco 1.2k ★
Google MCP Security Servers — Security Operations and Threat Intelligence MCP servers 453 ★

README

Sentinel · Local vulnerability monitoring

A local Windows + WSL dashboard that combines observed software inventory, CISA known-exploitation intelligence, OSV dependency checks, and live web research by **Codex or Claude Code**. Findings explain which installation an advisory may affect, cite the evidence, and propose fixes to inspect and copy.

![Sentinel dashboard in a clean workspace](docs/images/dashboard.jpg)

*Actual application screenshot from an empty workspace, paused for documentation. No sample findings or device inventory are published.*

Method and quick start

Each investigation collects Windows/WSL versions, scans explicitly configured project folders with OSV-Scanner, fetches CISA KEV, then asks the selected agent to research vendor advisories and exploitation reports. Validated records are saved in SQLite and streamed to the dashboard. Assessments distinguish **affected**, **potentially affected**, **not affected**, and **unknown**; exploitation evidence is tracked separately. See [coverage and evidence boundaries](docs/coverage.md).

Run in **native Windows PowerShell**. Install [uv](https://docs.astral.sh/uv/getting-started/installation/), the [native Codex CLI](https://learn.chatgpt.com/docs/enterprise/windows-deployment) and/or [Claude Code](https://code.claude.com/docs/en/setup), plus [OSV-Scanner v2](https://google.github.io/osv-scanner/installation/). Complete `codex login` and/or `claude auth login` under your Windows account. The [setup guide](docs/setup.md#install-tools-and-sign-in) includes installation commands, executable-path troubleshooting, and WSL scanner setup.

git clone https://github.com/BurnyCoder/security-monitoring-agent.git
cd security-monitoring-agent
uv sync --locked
Copy-Item .env.example .env
uv run security-monitoring-agent diagnostics
uv run security-monitoring-agent serve

Open [the dashboard](http://127.0.0.1:8765). Choose a provider and model, then **Run scan**. The default model is `gpt-6-lu