SKILLEMALL.ai
GitHub ↗ RU Sign in

BD skill_guard

Skill Security Scanner - Scan for risks before download/use. Use when: installing unknown skills, evaluating third-party code, or security auditing. / Skill安全检查 - 下载/使用前检测风险。

ClawHub Agent Skills author: HuaiBuer v1.3.0 MIT-0 3 files body ≈ 392 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 37/100 · Unfinished process — weak spots: steps, result and completion, when it triggers

AnalyzerSoftware developmentInfrastructuretype 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
89/100
safety, quality, tests
Safety 60%
98
Quality 40%
76
Run on models
none yet
Process rating
D
37/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Dangerous commands cmd-privilege skill_guard.py:86
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      (["chmod 777", "chown", "setuid", "sudo", "privilege"], "权限提升", "🟠 高"),
      code literalsecurity skill
    • low Risky intent intent-offensive-security SKILL.md:59
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      'virus_backdoor': ['ransomware', 'miner', 'backdoor'],
      quoted

    Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)

    Process rating: all ten parameters 37/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 25Steps. 1 steps
    • 40Consistency. Frontmatter name (skill_guard) differs from the folder (skill-guard-waai)
    • 100Tools and files. No external tools needed
    • 100Execution cost. Instruction body is 392 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)
    • +3No numbered steps or checklist
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 174: enough signal without eating the budget
    • +4Structure: 7 headings
    • +4Has examples (3 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

    External checks

    ClawHub: clean
    This is a lightweight local keyword scanner for skills, with no evidence of hidden execution, network access, persistence, or data exfiltration.
    LLM: benign (high) · VirusTotal: · 29 May 2026