# update-threat-db

update-threat-db — a skill for Claude Code and Codex that refreshes threat intelligence and IOC feeds via AgentSec Triage. Synchronizes security advisories for coding agents and MCP tools.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 6529 repo stars
- Author: FlorianBruniaux
- License: CC-BY-SA-4.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/HEAD/.agents/skills/update-threat-db/SKILL.md
- Updated: 2026-11-14
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/update-threat-db

## What it does

Processes recent security alerts for coding agents, MCP integrations, and malicious repository dumps before updating the security intelligence feed. The skill ingests indicators from raw tables and gist files while strictly avoiding cloning unverified archives or running suspicious samples.

Each accepted entry requires a dedicated regression check, alias deduplication across CVE and GHSA IDs, and status tagging such as partial or detected. After passing AgentSec validation gates, the workflow aligns consumer artifacts and verifies byte equality across public feeds.

Executing the routine requires Python 3 for `scripts/sync-threat-skill.py`. The environment must also provide the `agentsec-triage` checkout locally or define its location via the `AGENTSEC_REPO` variable.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill update-threat-db -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/update-threat-db/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/update-threat-db/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill update-threat-db -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/update-threat-db/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill update-threat-db -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/update-threat-db/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install FlorianBruniaux/claude-code-ultimate-guide .agents/skills/update-threat-db
```

2. **Manually: put the files in place**
- File: `.github/skills/update-threat-db/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill update-threat-db -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/FlorianBruniaux/claude-code-ultimate-guide --path .agents/skills/update-threat-db
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/update-threat-db/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/HEAD/.agents/skills/update-threat-db/SKILL.md

## When to use it
- refresh threat intelligence records for coding agents and MCP servers
- evaluate researcher indicator dumps without executing untrusted code
- correlate new attack waves with established malware families
- synchronize public security feeds and compatibility documentation

## Example prompts
- Update the threat database with recent MCP security advisories via AgentSec Triage
- Review this list of repository indicators and add regression tests for detection
- Synchronize the approved security feed and verify drift with sync-threat-skill.py

## Similar
- [analyzing-threat-actor-ttps-with-mitre-attack](https://affpapa.org/en/nevibecode/skills/analyzing-threat-actor-ttps-with-mitre-attack.md) — skill · 323 installs
- [Proofpoint MCP](https://affpapa.org/en/nevibecode/mcp/proofpoint-mcp.md) — MCP server · ★ 87 repo stars
- [intelthreadlinqs-mcp](https://affpapa.org/en/nevibecode/mcp/intelthreadlinqs-mcp.md) — MCP server
- [Truss Threat Intelligence](https://affpapa.org/en/nevibecode/mcp/truss-threat-intelligence.md) — MCP server
- [analyzing-indicators-of-compromise](https://affpapa.org/en/nevibecode/skills/analyzing-indicators-of-compromise.md) — skill · 483 installs
- [threat-detection](https://affpapa.org/en/nevibecode/skills/threat-detection.md) — skill · 637 installs

From the same set: [florianbruniaux/claude-code-ultimate-guide](https://affpapa.org/en/nevibecode/by/florianbruniaux/claude-code-ultimate-guide.md) — 45 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
