SKILLEMALL.ai
GitHub ↗ RU Sign in

BB vagrant

Disposable VMs for safe testing — full sudo, Docker, Go, nested KVM, destroy and recreate. Use when you need a sandbox to build, test, or break things without affecting the host. Use when the user says "spin up a VM", "test in isolation", "run with sudo", "try something dangerous", "set up a dev environment", "I need Docker", "test firewall rules", "clean environment", or needs root access, network testing, or safe experimentation.

ClawHub Agent Skills author: jpoley v0.7.4 MIT-0 14 files · 5 scripts body ≈ 3 463 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 72/100 · Nearly there — weak spots: result and completion, consistency, progress reporting

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
B
81/100
safety, quality, tests
Safety 60%
75
Quality 40%
89
Run on models
none yet
Process rating
B
72/100
Nearly there
Result and completion w 14
0
Progress reporting w 2
0
Consistency w 8
40
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 · 13

    ✓ No critical or high findings

    Medium and low: 13
    • medium Dangerous commands cmd-disable-security examples/nginx-hardened/scripts/provision.sh:35
      Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (test fixture / example file)
      iptables -F INPUT
      fixture
    • medium Dangerous commands cmd-disable-security examples/nginx-hardened/scripts/provision.sh:36
      Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (test fixture / example file)
      iptables -F OUTPUT
      fixture
    • medium Dangerous commands cmd-disable-security examples/nginx-hardened/scripts/provision.sh:37
      Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (test fixture / example file)
      iptables -F FORWARD
      fixture
    • low Dangerous commands cmd-background-process examples/mac-docker-compose/scripts/provision.sh:47
      Starts a background / autostarted process (test fixture / example file)
      systemctl enable --now docker
      fixture
    • low Dangerous commands cmd-disable-security examples/nginx-hardened/scripts/provision.sh:6
      Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (detector / deny-list definition; string literal in code, not executed; code comment; test fixture / example file)
      #   `iptables -F INPUT` clears all rules immediately. If you then set
      detectorcode literalcommentfixture
    • low Dangerous commands cmd-background-process examples/nginx-hardened/scripts/provision.sh:65
      Starts a background / autostarted process (test fixture / example file)
      systemctl enable nginx
      fixture
    • low Dangerous commands cmd-background-process examples/windows-systemd-service/scripts/provision.sh:100
      Starts a background / autostarted process (test fixture / example file)
      systemctl enable demo-http
      fixture
    • low Dangerous commands cmd-background-process scripts/setup.sh:90
      Starts a background / autostarted process
      systemctl enable --now docker
    • low Dangerous commands cmd-background-process SKILL.md:145
      Starts a background / autostarted process (documentation of a security skill)
      systemctl enable --now docker
      security skill
    • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:158
      Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
      #   curl -fsSL https://deb.nodesource.com/setup_22.x | bash -
      security skill

    A further 3 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 14. 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 72/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 40Consistency. Frontmatter name (vagrant) differs from the folder (vagrant-skill)
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 50 steps
    • 100Failures and branches. 2 branches, has a failure section
    • 100Execution cost. Instruction body is 3463 tokens
    • 100Running it twice. Mutating operations check current state
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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

    • +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
    • -32 of 2 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +5Description quotes 8 example trigger phrases
    • +3Description length 435: enough signal without eating the budget
    • +4Structure: 30 headings
    • +3Step-by-step instructions: 50 items
    • +4Has examples (20 code blocks)
    • +4Reference files are cited in the instructions (2 of 4)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: suspicious
    This VM sandbox skill mostly does what it claims, but it needs review because its default template forwards the user's SSH agent into a VM meant for risky experimentation.
    LLM: suspicious (high) · VirusTotal: · 28 May 2026