SKILLEMALL.ai
GitHub ↗ RU Sign in

AB openclaw-audit

Audit your OpenClaw configuration against 12 production primitives PLUS 8 common setup footguns (silent cost leaks, prompt-injection paths, zombie session state, dead fallbacks). Returns a severity-ranked assessment with specific fixes. Use after initial setup, after major config changes, before deploying to a new machine, or when something feels off but you can't pinpoint why.

ClawHub Agent Skills author: Shawn Petros v1.2.0 MIT-0 2 files body ≈ 2 330 tokens Open the sourceclawhub.ai↗ analyzed 7 d ago

Audit your OpenClaw configuration against 12 production primitives PLUS 8 common setup footguns (silent cost leaks, prompt-injection paths, zombie session…

As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions

AnalyzerSlackAI and agentsWriting and documentsInfrastructuretype 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
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
87
Run on models
none yet
Process rating
B
67/100
Nearly there
Inputs and preconditions w 11
0
When it triggers w 12
20
Failures and branches w 10
50
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 · 0

    ✓ No critical or high findings

    Files scanned: 2. 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 67/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Result and completion. Output format stated, no completion criterion
    • 85Steps. 86 steps, 1 vague phrases
    • 100Tools and files. No external tools needed
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2330 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress

    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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 380: enough signal without eating the budget
    • +4Structure: 30 headings
    • +3Step-by-step instructions: 86 items
    • +3Output format is stated explicitly
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: suspicious
    This audit skill has a legitimate OpenClaw security-audit purpose, but it asks the agent to inspect sensitive local OpenClaw secrets, auth, session, and workspace files more broadly than necessary.
    LLM: suspicious (high) · VirusTotal: · 16 Sept 2026