SKILLEMALL.ai
GitHub ↗ RU Sign in

BC openclaw-security-audit

Use when auditing and remediating an OpenClaw Linux host with a nightly 23:00 security run. Covers firewall status, fail2ban bans, SSH hardening with key-only auth and a non-default port, unexpected listening ports, Docker container allowlisting, disk usage under 80%, failed login attempts in the last 24 hours, automatic security package updates, VirusTotal browser-based checks for URLs and files without API keys, and installing the cron entry.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: scorpion7slayer v0.1.3 MIT-0 5 files · 3 scripts body ≈ 1 644 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

AnalyzerDockerInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
78
Quality 40%
82
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Consistency w 8
40
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

  • high Dangerous commands cmd-persistence scripts/install_cron.sh:34
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    } | crontab -
Medium and low: 4
  • low Dangerous commands cmd-cron-mention scripts/install_cron.sh:22
    Mentions editing / listing crontab
    crontab -l 2>/dev/null > "${CURRENT_CRONTAB}" || true
  • low Dangerous commands cmd-background-process scripts/openclaw_security_audit.sh:109
    Starts a background / autostarted process (documentation of a security skill)
    if run_privileged systemctl enable --now "${service}" >/dev/null 2>&1; then
    security skill
  • low Dangerous commands cmd-background-process scripts/openclaw_security_audit.sh:525
    Starts a background / autostarted process (documentation of a security skill)
    run_privileged systemctl enable --now unattended-upgrades >/dev/null 2>&1 || true
    security skill
  • low Dangerous commands cmd-background-process scripts/openclaw_security_audit.sh:563
    Starts a background / autostarted process (documentation of a security skill)
    run_privileged systemctl enable --now "${timer_service}" >/dev/null 2>&1 || return 1
    security skill

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 57/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (openclaw-security-audit) differs from the folder (nxtsecure-openclaw)
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 57 steps, 1 vague phrases
  • 100Failures and branches. 8 branches, has a failure section
  • 100Execution cost. Instruction body is 1644 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (6 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 448: enough signal without eating the budget
  • +4Structure: 7 headings
  • +3Step-by-step instructions: 57 items
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

External checks

ClawHub: suspicious
This appears to be a real OpenClaw host hardening skill, but it can make persistent privileged system changes automatically and needs careful review before use.
LLM: suspicious (high) · VirusTotal: · 29 May 2026