SKILLEMALL.ai
RU Sign in

AB 3x-ui-vps

Deploy and manage 3X-UI on a root-managed Ubuntu or Debian VPS using Docker Compose, nginx, ACME certificates, SSH panel tunneling, UFW hardening, and Xray VLESS over XHTTP behind nginx. Use when the user explicitly wants to install 3X-UI from scratch, lock the panel and subscription server to 127.0.0.1, open an SSH tunnel to the panel, create or repair a VLESS inbound behind nginx on public 443, add extra clients to an existing inbound, or run safe OS and container updates.

ClawHub Agent Skills author: olegtsvetkov v1.1.0 MIT-0 12 files · 4 scripts body ≈ 2 525 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 73/100 · Nearly there — weak spots: result and completion, running it twice

GeneratorDockerInfrastructuretype 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
A
92/100
safety, quality, tests
Safety 60%
94
Quality 40%
90
Run on models
none yet
Process rating
B
73/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
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

    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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • medium Dangerous commands cmd-pipe-to-shell scripts/bootstrap-host.sh:337
      Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
      curl -fsSL https://get.acme.sh | sh -s email="${ACME_EMAIL:-}"
      vendor-host
    • low Dangerous commands cmd-background-process scripts/bootstrap-host.sh:317
      Starts a background / autostarted process
      systemctl enable --now nginx

    Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 73/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 13 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 79 steps
    • 100When it triggers. States when to use and when not to
    • 100Failures and branches. 11 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2525 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • high The skill tells the model to perform an irreversible action with no human approval
    • low The response is described with custom markup (5 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
    • -2localhost URLs: will not work for another user
    • +2Single-language instructions
    • +3Description length 479: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 79 items
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)
    • +3All 6 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

    External checks

    ClawHub: suspicious
    This skill appears purpose-built for VPS administration, but it deserves review because it can make broad root-level server changes and has under-disclosed safety gaps.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026