SKILLEMALL.ai
GitHub ↗ RU Sign in

AC claw-security-self-check

Perform a strict, evidence-based, read-only security assessment of the current OpenClaw host, review each NOT_TESTED item through targeted OpenClaw Agent investigation, and merge structured review evidence into a formal audit report. Also use this Skill to generate reports offline from existing baseline JSON and manual-review JSON files.

ClawHub Agent Skills author: Xiaoyiyi23 v0.1.0 MIT-0 10 files · 2 scripts body ≈ 1 651 tokens Open the sourceclawhub.ai↗ analyzed 15 d ago

Perform a strict, evidence-based, read-only security assessment of the current OpenClaw host, review each NOTTESTED item through targeted OpenClaw Agent…

As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerData and analyticstype 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
96/100
safety, quality, tests
Safety 60%
98
Quality 40%
92
Run on models
none yet
Process rating
C
62/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Risky intent intent-offensive-security references/check-matrix.md:24
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - `PASS` means that observable effective configuration and runtime state meet the check requirements. It does not mean that penetration testing was performed.
    • low Risky intent intent-offensive-security references/evidence-rules.md:43
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - `PASS` means only that the observed configuration and state comply. It does not mean that penetration testing or behavioral bypass testing was performed.

    Files scanned: 10. 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 62/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 65Failures and branches. 3 branches
    • 100Tools and files. No external tools needed
    • 100Steps. 40 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1651 tokens
    • 100Running it twice. No mutating operations
    • 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)
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +3Description length 339: enough signal without eating the budget
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 40 items
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)
    • +3All 2 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

    External checks

    ClawHub: clean
    This skill is a disclosed read-only OpenClaw security audit helper that generates local reports without remediation or hidden persistence.
    LLM: benign (high) · VirusTotal: · 22 Jul 2026