SKILLEMALL.ai
GitHub ↗ RU Sign in

AD openclaw-guard-skill

Local VAIBot Guard skill for OpenClaw. Use to run the guard service, enforce tool decisions via the OpenClaw circuit-breaker plugin, manage approvals, and validate guard receipts/audit logs. Also use when installing/operating the guard systemd user service or running guard unit tests.

ClawHub Agent Skills author: Briant Anthony v0.2.1 MIT-0 25 files body ≈ 534 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerSoftware developmentInfrastructureSecuritytype 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
90/100
safety, quality, tests
Safety 60%
94
Quality 40%
83
Run on models
none yet
Process rating
D
47/100
Unfinished process
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration 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 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.

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 Exfiltration net-redirectable-api-key scripts/vaibot-guard-service.mjs:65
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • low Dangerous commands cmd-background-process references/ops-runbook.md:105
      Starts a background / autostarted process (documentation of a security skill)
      sudo systemctl enable --now vaibot-guard
      security skill

    Files scanned: 24. 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 47/100

    • 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
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (openclaw-guard-skill) differs from the folder (vaibot-guard)
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 100Steps. 18 steps
    • 100Execution cost. Instruction body is 534 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

    • +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
    • -32 of 4 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 285: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 18 items
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (6 of 13)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: suspicious
    The skill appears to be a legitimate local guard, but it needs review because it can persist as a service, execute guarded commands, and send execution metadata to VAIBot when API credentials are configured.
    LLM: suspicious (medium) · VirusTotal: · 29 May 2026