SKILLEMALL.ai
GitHub ↗ RU Sign in

CB linux-firewall-hardening

Safe Linux firewall hardening with backend detection, idempotent atomic rules, rollback protection, and AI-executable state-machine workflows. Covers ufw, firewalld, nftables, iptables, Docker, Kubernetes CNI awareness, and fail2ban with compliance mapping to CIS/PCI-DSS/SOC2.

ClawHub Agent Skills author: discovery219 v2.7.0 MIT-0 23 files · 6 scripts body ≈ 6 023 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 70/100 · Nearly there — weak spots: result and completion, when it triggers

AnalyzerDockerKubernetesInfrastructuretype 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
C
67/100
safety, quality, tests
Safety 60%
63
Quality 40%
73
Run on models
none yet
Process rating
B
70/100
Nearly there
When it triggers w 12
20
Result and completion w 14
40
Tools and files w 18
60
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 17

✓ No critical or high findings

Medium and low: 17
  • medium Dangerous commands cmd-disable-security references/recovery.md:14
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)
    sudo ufw reset && sudo ufw disable
    security skill
  • medium Dangerous commands cmd-disable-security references/recovery.md:18
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)
    sudo iptables -P INPUT ACCEPT; sudo iptables -F
    security skill
  • medium Dangerous commands cmd-disable-security references/recovery.md:21
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)
    sudo ufw disable
    security skill
  • medium Dangerous commands cmd-persistence scripts/audit-firewall.sh:139
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    elif [[ -f /etc/cron.d/ansible-pull ]] || (crontab -l 2>/dev/null | grep -qi ansible); then
    security skill
  • medium Dangerous commands cmd-disable-security SKILL.md:248
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)
    systemctl is-active ufw &>/dev/null && sudo ufw disable
    security skill
  • low Dangerous commands cmd-privilege references/backend-nftables.md:27
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo tee /etc/nftables.conf.new << 'EOF'
    security skill
  • low Dangerous commands cmd-privilege references/backend-nftables.md:86
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo mv /etc/nftables.conf.new /etc/nftables.conf
    security skill
  • low Dangerous commands cmd-background-process references/backend-nftables.md:89
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable nftables
    security skill
  • low Dangerous commands cmd-privilege references/observability.md:72
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo tee -a /etc/sysctl.d/99-f…onf << 'EOF'
    security skill
  • low Dangerous commands cmd-background-process references/security-profiles.md:100
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable nftables
    security skill
  • low Dangerous commands cmd-cron-mention scripts/audit-firewall.sh:139
    Mentions editing / listing crontab (documentation of a security skill)
    elif [[ -f /etc/cron.d/ansible-pull ]] || (crontab -l 2>/dev/null | grep -qi ansible); then
    security skill
  • low Dangerous commands cmd-disable-security SKILL.md:59
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (negated — the text forbids it)
    2. **Never run `iptables -F` or `nft flush ruleset` without a verified backup.** Docker/K8s networking will break.
    negated

A further 5 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6023 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "title"
  • note frontmatter-key unknown frontmatter key "skill_version"
  • note frontmatter-key unknown frontmatter key "schema_version"

Process rating: all ten parameters 70/100

  • 20When it triggers. No condition that starts the skill
  • 40Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6023 tokens
  • 100Steps. 82 steps
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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 16 top-level sections: this looks like several domains in one skill

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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -217 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 277: enough signal without eating the budget
  • +4Structure: 33 headings
  • +3Step-by-step instructions: 82 items
  • +4Has examples (15 code blocks)
  • +4Reference files are cited in the instructions (13 of 14)
  • +3All 6 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: suspicious
This firewall-hardening skill is purpose-aligned, but its automated recovery and verification scripts can make broad privileged system changes beyond the approved firewall plan.
LLM: suspicious (high) · 7 Aug 2026