# openclaw-audit-watchdog

The skill runs a deep security audit of OpenClaw agents on a schedule and sends the report as a direct message. Email delivery is optional.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 751 installs · ★ 1125
- Author: prompt-security
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/prompt-security/clawsec/tree/HEAD/skills/openclaw-audit-watchdog/SKILL.md
- Updated: 2026-10-25
- HTML: https://affpapa.org/en/nevibecode/skills/openclaw-audit-watchdog

## What it does

The skill creates or updates an `openclaw cron` job that runs `openclaw security audit --json` and `openclaw security audit --deep --json` every day. Findings are summarised into critical, warn, info and top findings. The report goes to the chosen channel and recipient, and an email copy is sent only when `PROMPTSEC_EMAIL_TO` is set. The default schedule is daily at 23:00 in the chosen timezone.

Runtime needs `bash`, `openclaw` and `node`. Email can go through a local `sendmail` or an SMTP relay via `PROMPTSEC_SMTP_HOST` and `PROMPTSEC_SMTP_PORT`. `git` is needed only when `PROMPTSEC_GIT_PULL=1`. The required variables are `PROMPTSEC_DM_CHANNEL` and `PROMPTSEC_DM_TO`.

The skill is not always-on. It creates an unattended job, so review the recipients and the host's `openclaw` environment first. For a standalone install there is a signed release manifest check: the `signing-public.pem` fingerprint, the `checksums.json` signature and the checksums for the archive, `SKILL.md` and `skill.json` are verified. Only extract the archive after that check passes.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install prompt-security/clawsec openclaw-audit-watchdog
```

2. **Manually: put the files in place**
- File: `.github/skills/openclaw-audit-watchdog/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/prompt-security/clawsec --path skills/openclaw-audit-watchdog
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a opencode
```

### 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/prompt-security/clawsec/tree/HEAD/skills/openclaw-audit-watchdog/SKILL.md

## When to use it
- Set up daily security audits for OpenClaw agents without running them by hand.
- Get the findings summary as a direct message, with an email copy.
- Verify the skill archive before installing it on a production host.

## Example prompts
- Set `PROMPTSEC_DM_CHANNEL` and `PROMPTSEC_DM_TO`, then run `/openclaw-audit-watchdog` — the job is created without prompts.
- Add `PROMPTSEC_EMAIL_TO` so the report also arrives by email.
- Set `PROMPTSEC_TZ` and `PROMPTSEC_HOST_LABEL` so the report carries the right timezone and host label.

## Similar
- [openclaw-config](https://affpapa.org/en/nevibecode/skills/openclaw-config.md) — skill · 2800 installs
- [healthcheck](https://affpapa.org/en/nevibecode/skills/healthcheck.md) — skill · 5500 installs
- [audit-chain](https://affpapa.org/en/nevibecode/commands/audit-chain.md) — command · ★ 41729
- [security-compliance-audit](https://affpapa.org/en/nevibecode/skills/security-compliance-audit.md) — skill · 665 installs
- [permission-auditor](https://affpapa.org/en/nevibecode/skills/permission-auditor.md) — skill · 476 installs
- [config-hardener](https://affpapa.org/en/nevibecode/skills/config-hardener.md) — skill · 468 installs

From the same set: [prompt-security/clawsec](https://affpapa.org/en/nevibecode/by/prompt-security/clawsec.md) — 2 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