openclaw-audit-watchdog: daily security audits for OpenClaw
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.
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a claude-codeWhat openclaw-audit-watchdog 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.
What it helps with
- 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 for the agent
- Set
PROMPTSEC_DM_CHANNELandPROMPTSEC_DM_TO, then run/openclaw-audit-watchdog— the job is created without prompts. - Add
PROMPTSEC_EMAIL_TOso the report also arrives by email. - Set
PROMPTSEC_TZandPROMPTSEC_HOST_LABELso the report carries the right timezone and host label.
How to install openclaw-audit-watchdog
1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a claude-code2Manually: put the files in place
~/.claude/skills/openclaw-audit-watchdog/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/openclaw-audit-watchdog/
1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a codex2Manually: put the files in place
.agents/skills/openclaw-audit-watchdog/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a cursor2Manually: put the files in place
.cursor/skills/openclaw-audit-watchdog/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install prompt-security/clawsec openclaw-audit-watchdog2Manually: put the files in place
.github/skills/openclaw-audit-watchdog/SKILL.md1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a gemini-cli2Platform CLI
gemini skills install https://github.com/prompt-security/clawsec --path skills/openclaw-audit-watchdogManually: put the files in place
.devin/skills/openclaw-audit-watchdog/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about openclaw-audit-watchdog
How do I install openclaw-audit-watchdog in Claude Code?
Run npx skills add prompt-security/clawsec --skill openclaw-audit-watchdog -a claude-code. The skill lands at ~/.claude/skills/openclaw-audit-watchdog/SKILL.md.
What does openclaw-audit-watchdog do?
It creates or updates a daily openclaw cron job that runs a standard and a deep security audit and sends the summary as a direct message, with an optional email copy.
How is it different from a similar skill?
It installs standalone from the ClawSec suite and verifies the signed release manifest before extracting the archive.
