SKILLEMALL.ai
GitHub ↗ RU Sign in

AC hostlink

Execute commands on the host machine from inside the OpenClaw container via the HostLink daemon. Provides secure, authenticated remote shell execution over a Unix domain socket (local) or TCP/WireGuard (remote). Use when you need to run commands on the host: access files outside the container, run host-side tools, interact with the Qwen3 merge project, manage Docker on the host, or execute anything requiring host-level access. The 'hostlink' binary is in PATH. Triggers on: "run on host", "execute on host", "host command", "outside container", "host machine", "hostlink", "hostlinkd".

ClawHub Agent Skills author: jebadiahgreenwood v0.1.0 MIT-0 3 files body ≈ 775 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

IntegrationDockerInfrastructuretype 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
93/100
safety, quality, tests
Safety 60%
95
Quality 40%
89
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • low Dangerous commands cmd-privilege references/setup.md:23
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo cp hostlinkd /usr/local/bin/
      security skill
    • low Dangerous commands cmd-privilege references/setup.md:30
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo tee /etc/hostlink/hostlink.conf << 'EOF'
      security skill
    • low Dangerous commands cmd-privilege references/setup.md:48
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo chmod 640 /etc/hostlink/hostlink.conf
      security skill
    • low Dangerous commands cmd-privilege references/setup.md:60
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo cp ~/hostlink/hostlink.service /etc/systemd/system/
      security skill
    • low Dangerous commands cmd-background-process references/setup.md:62
      Starts a background / autostarted process (documentation of a security skill)
      sudo systemctl enable hostlinkd
      security skill

    Files scanned: 3. 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 57/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 5 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 775 tokens
    • 100Running it twice. No mutating operations

    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
    • -4Absolute local paths (C:\Users, /home/…): not portable
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 7 example trigger phrases
    • +3Description length 589: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 5 items
    • +4Has examples (7 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)

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

    External checks

    ClawHub: suspicious
    HostLink is clear about enabling host command execution, but it creates a persistent, high-impact bridge from the container to the host with broad scope and limited safeguards.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026