SKILLEMALL.ai
RU Sign in

DB linux-security-guardian

Autonomous multi-client Linux server security management via SSH MCP. Runs full audit at 1 AM IST nightly via cron. Iterates over all clients and their server fleets. Covers system hardening, CVE scanning (CISA KEV + OSV.dev + NVD API), user auditing, SSH config (incl. weak ciphers/MACs/Kex), firewall rules, running services, file permissions, log analysis, SSL certs, kernel parameters (incl. BPF restrictions), Docker daemon security defaults (userns-remap, no-new-privileges, seccomp), fail2ban auto-install, unattended-upgrades auto-enable, CIS benchmark scoring, systemd sandbox analysis, AppArmor/SELinux audit, and swap encryption check. Non-breaking actions auto-applied. Critical patches and network/firewall changes require owner confirmation. Report sent per-server and per-client via email plugin/skill (not bundled). All owner-specific config lives in core-extra/config/ — no hardcoded names, domains, or emails.

Not recommendedlow grade D
ClawHub Agent Skills author: vk v1.6.0 MIT-0 49 files · 2 scripts body ≈ 3 783 tokens Open the sourceclawhub.ai↗ analyzed 10 h ago

Autonomous multi-client Linux server security management via SSH MCP.

As a process B 72/100 · Nearly there — weak spots: result and completion, when it triggers

AnalyzerDockerSecurityAI and agentsData and analyticstype 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
D
59/100
safety, quality, tests
Safety 60%
53
Quality 40%
69
Run on models
none yet
Process rating
B
72/100
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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 27

✓ No critical or high findings

Medium and low: 27
  • medium Dangerous commands cmd-persistence audit/modules/13-crons.md:6
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    cat /etc/crontab 2>/dev/null
    security skill
  • medium Dangerous commands cmd-persistence audit/modules/13-crons.md:7
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    ls -la /etc/cron.d/ 2>/dev/null
    security skill
  • medium Dangerous commands cmd-persistence audit/modules/13-crons.md:8
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    cat /etc/cron.d/* 2>/dev/null
    security skill
  • medium Dangerous commands cmd-persistence audit/modules/13-crons.md:9
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    ls /etc/cron.hourly/ /etc/cron.daily/ /etc/cron.weekly/ /etc/cron.monthly/ 2>/dev/null
    security skill
  • medium Broad scope meta-agent-memory-dump SOUL.md
    Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
    SOUL.md
  • low Risky intent intent-offensive-security AGENT.md:107
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - KEV + Ransomware (🔥 highest priority)
  • low Risky intent intent-offensive-security AGENT.md:151
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    Source override flags: KEV → CRITICAL, RANSOMWARE → 🔥 immediate alert, OSV_MATCH → per CVSS, NVD_CORROBORATED → +1 severity.
    detector
  • low Dangerous commands cmd-background-process audit/modules/05-services.md:55
    Starts a background / autostarted process (documentation of a security skill)
    - systemctl enable auditd + systemctl start auditd
    security skill
  • low Risky intent intent-offensive-security audit/modules/07-cve.md:157
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)
    | `RANSOMWARE` | CISA KEV (knownRansomwareCampaignUse) | 🔥 Highest priority — immediate alert + confirm within due date |
    table
  • low Risky intent intent-offensive-security audit/modules/07-cve.md:193
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **Flags:** KEV | RANSOMWARE | OSV_MATCH | NVD_CORROBORATED
  • low Risky intent intent-offensive-security audit/modules/07-cve.md:213
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    [CRITICAL][RANSOMWARE] 07-cve: CVE-…ZZZ | package: nginx | cvss: 7.5 | kev: ransomware_known | due: 2024-06-15 | action_id: ACT-ZZZ
    detector
  • low Risky intent intent-offensive-security audit/modules/10-filesystem.md:38
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - Unexpected SUID → HIGH (possible privilege escalation vector)
    detector
  • low Risky intent intent-offensive-security audit/modules/11-kernel.md:66
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - BPF has been used in multiple privilege escalation exploits (CVE-…994, CVE-…835, etc.)
  • low Dangerous commands cmd-cron-mention audit/modules/13-crons.md:13
    Mentions editing / listing crontab (documentation of a security skill)
    crontab -l -u $user 2>/dev/null && echo "=== $user ==="
    security skill
  • low Risky intent intent-offensive-security audit/modules/15-docker.md:81
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    | no-new-privileges | true | MEDIUM (prevents privilege escalation via suid) |
    detector
  • low Risky intent intent-offensive-security audit/modules/20-systemd-analyze.md:41
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | NoNewPrivileges | `true` | Prevents privilege escalation via SUID |
  • low Risky intent intent-offensive-security audit/modules/21-mount-hardening.md:45
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - /dev/shm without noexec → **HIGH** (often used in privilege escalation exploits)
    detector
  • low Dangerous commands cmd-background-process audit/modules/25-usbguard.md:75
    Starts a background / autostarted process (documentation of a security skill)
    systemctl enable --now usbguard
    security skill
  • low Risky intent intent-offensive-security hooks/audit-runner.md:114
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    # Labels: KEV → CRITICAL, RANSOMWARE → 🔥 FIRE on-critical.md
    detector
  • low Secrets in code secret-high-entropy-token hooks/on-confirm-reply.md:17
    High-entropy token-like string (may be an id, hash or a credential)
    Example: clie…001
  • low Risky intent intent-offensive-security hooks/on-critical.md:46
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | KEV + RANSOMWARE | 🚨🔥 | "🚨🔥" |
  • low Risky intent intent-offensive-security hooks/on-critical.md:57
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - If ransomware-flagged, add to body: `"⚠️ Used in known ransomware campaigns — patch IMMEDIATELY"`
  • low Risky intent intent-offensive-security SKILL.md:146
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | CVE — KEV + Ransomware | any | **🔥 HIGHEST PRIORITY** — immediate alert, confirm ASAP |
  • low Exfiltration exfil-read-secret-files SKILL.md:178
    Reads credential / secret files (documentation table row; documentation of a security skill)
    | `02-users` | Accounts, root access, sudo, empty passwords, inactive | `ssh_exec(op="run", sessionId, command="cat /etc/passwd; cat /etc/shadow; ...")` |
    tablesecurity skill
  • low Secrets in code secret-high-entropy-token SKILL.md:233
    High-entropy token-like string (may be an id, hash or a credential)
    (Full ID format: <client>-<server>-<type>-<NNN>, e.g. clie…001)

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 49. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note edit-residue the text marks something as outdated (lines 7): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 72/100

  • 20When it triggers. No condition that starts the skill
  • 40Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 14 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3783 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 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (12 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)
  • +3Description length 927: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 21 headings
  • +3Step-by-step instructions: 14 items
  • +4Has examples (12 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
This skill is a disclosed Linux security automation tool, but it needs Review because it can run high-impact root SSH actions across multiple client servers on a permanent schedule with weak bulk-approval and data-boundary controls.
LLM: suspicious (high) · VirusTotal: · 14 Jul 2026