SKILLEMALL.ai
GitHub ↗ RU Sign in

FC 3x-ui-setup

Complete VPN server setup from scratch. Takes a fresh VPS (IP + root + password from hosting provider) through full server hardening and 3x-ui (Xray proxy panel) installation with VLESS Reality or VLESS TLS. Guides user through connecting via Hiddify client. Use when user mentions v2ray, xray, vless, 3x-ui, proxy server, vpn server, or wants to set up encrypted proxy access on a VPS. Designed for beginners — hand-holds through every step.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: Mikhail v1.0.0 5 files body ≈ 9 818 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

ProcedureInfrastructuretype 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
F
35/100
safety, quality, tests
Safety 60%
7
Quality 40%
78
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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. 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.
  2. 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 · 21

  • high Exfiltration exfil-send-secrets-to-url SKILL.md:673
    Instruction to send secrets/history to an external endpoint (documentation of a security skill)
    После создания ключа отправь публичный ключ на сервер (следующий шаг).
    security skill
  • high Exfiltration exfil-send-secrets-to-url SKILL.md:681
    Instruction to send secrets/history to an external endpoint (documentation of a security skill)
    Отправь публичный ключ на сервер (из терминала на ноутбуке):
    security skill
  • high Exfiltration exfil-send-secrets-to-url SKILL.md:841
    Instruction to send secrets/history to an external endpoint (documentation of a security skill)
    # Отправить публичный ключ на сервер
    security skill
  • high Exfiltration exfil-send-secrets-to-url SKILL.md:867
    Instruction to send secrets/history to an external endpoint (documentation of a security skill)
    # Отправить публичный ключ на сервер
    security skill
Medium and low: 17
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write Edit
  • low Dangerous commands cmd-privilege references/fallback-nginx.md:41
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo ln -sf /etc/nginx/sites-available/stub /etc/nginx/sites-enabled/stub && sudo rm -f /etc/nginx/sites-enabled/default && sudo nginx -t && sudo systemctl reload nginx"
    security skill
  • low Dangerous commands cmd-privilege SKILL.md:220
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo tee /etc/sysctl.d/99-s…onf << 'EOF'
    security skill
  • low Dangerous commands cmd-background-process SKILL.md:241
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable chrony
    security skill
  • low Dangerous commands cmd-background-process SKILL.md:622
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable fail2ban && sudo systemctl restart fail2ban'
    security skill
  • low Dangerous commands cmd-background-process SKILL.md:732
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable fail2ban
    security skill
  • low Dangerous commands cmd-background-process SKILL.md:984
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable fail2ban && sudo systemctl restart fail2ban'
    security skill

A further 10 matches are quotations in this security skill's documentation and are not counted as findings.

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

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 9818 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 14 mutating operations with no state check
  • 40Consistency. Frontmatter name (3x-ui-setup) differs from the folder (3x-ui-vpn-setup)
  • 40Execution cost. Instruction body is 9818 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 85Steps. 79 steps, 1 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100Failures and branches. 12 branches, has a failure section
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 38 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
  • -2localhost URLs: will not work for another user
  • +1No license
  • +3Description length 442: enough signal without eating the budget
  • +4Structure: 64 headings
  • +3Step-by-step instructions: 79 items
  • +4Has examples (69 code blocks)
  • +4Reference files are cited in the instructions (1 of 2)
  • +2Bilingual instructions (RU + EN)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
This VPN setup skill is mostly coherent, but it includes risky credential handling and an optional fake login fallback page that users should review carefully before installing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026