# update-threat-db

The update-threat-db command delegates threat database changes to AgentSec and checks the resulting feed, catalogue, and compatibility data.

- command · `type=command` · Claude Code, Codex, GitHub Copilot, Gemini CLI · ★ 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/.claude/commands/update-threat-db.md
- Updated: 2026-10-22
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/commands/update-threat-db

## What it does

\`update-threat-db` routes threat evidence and database maintenance to the AgentSec checkout. It resolves that checkout from `AGENTSEC_REPO` or `../agentsec-triage`, verifies the required files, and runs `.claude/commands/update-threat-db.md` there. AgentSec handles source review, detector coverage, regression checks, and generated artifacts.

Once that workflow passes, the command copies the generated feed into the guide with `scripts/sync_security_feed.py --write`, repeats the check mode, and runs the listed feed tests. It also refreshes the landing catalogue. The legacy `examples/commands/resources/threat-db.yaml` remains a consumer for `/security-check` and `/security-audit`. The process stops when the AgentSec checkout or its required files cannot be found; cloning, pulling, and publishing need explicit authorization.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/update-threat-db.md` — Call it with /update-threat-db. For all projects use ~/.claude/commands/

### Codex

**Manually: put the files in place**
- File: `~/.codex/prompts/update-threat-db.md` — Call it with /prompts:update-threat-db. Codex marks this format deprecated in favour of skills

### GitHub Copilot

**Manually: put the files in place**
- File: `.github/prompts/update-threat-db.prompt.md`

### Gemini CLI

**Manually: put the files in place**
- File: `.gemini/commands/update-threat-db.toml` — Gemini stores commands as TOML: the prompt text goes into the prompt field

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/.claude/commands/update-threat-db.md

## When to use it
- delegate threat database updates to AgentSec
- sync the security feed into the guide
- refresh the landing search catalogue
- keep `/security-check` and `/security-audit` compatible
- run feed and catalogue validation

## Example prompts
- Run `update-threat-db` and route the threat database update through AgentSec.
- Check the guide and landing after synchronizing the security feed.
- Run the update without cloning or publishing repositories unless authorization is explicit.

## Similar
- [threat-modeling](https://affpapa.org/en/nevibecode/skills/devops-skills-threat-modeling.md) — skill · 396 installs
- [threat-model-generation](https://affpapa.org/en/nevibecode/skills/threat-model-generation.md) — skill · 151 installs
- [update-dependencies](https://affpapa.org/en/nevibecode/commands/update-dependencies.md) — command · 356 installs
- [mantis-threat-model](https://affpapa.org/en/nevibecode/skills/mantis-threat-model.md) — skill · 1900 installs
- [threat-model](https://affpapa.org/en/nevibecode/skills/anthropics-threat-model.md) — skill · 1300 installs
- [threat-modeling-expert](https://affpapa.org/en/nevibecode/skills/threat-modeling-expert.md) — skill · 73 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
