SKILLEMALL.ai

BD guomeiqing-safe-install

Safely review and install third-party OpenClaw Skills. Downloads to a temp directory, runs a 7-point security audit, generates a human-readable report, and only installs if safe. Use when asked to "安装 skill", "install skill", "帮我装", "add skill", or "safe install".

ClawHub Agent Skills author: shanggqm v1.1.0 MIT-0 5 files body ≈ 2 421 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerData and analyticsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
88/100
safety, quality, tests
Safety 60%
88
Quality 40%
87
Run on models
none yet
Process rating
D
43/100
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 · 12

    ✓ No critical or high findings

    Medium and low: 12
    • low Risky intent intent-offensive-security README.en.md:29
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | 5 | 🔓 Privilege Escalation | Elevated permissions, modifying system configs |
    • low Risky intent intent-offensive-security README.en.md:55
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      5. ✅ Privilege Escalation — None found
    • low Risky intent intent-offensive-security SKILL.en.md:179
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Reverse shell patterns (`nc`, `/dev/tcp`, `mkfifo`) | 🔴 DANGER | Remote control |
    • low Risky intent intent-offensive-security SKILL.en.md:206
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Review Item 5: Privilege Escalation 🔓
    • low Dangerous commands cmd-privilege SKILL.en.md:224
      Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)
      | Requests `chmod 777` or overly permissive access | 🔴 DANGER | Reduces security |
      tablesecurity skill
    • low Risky intent intent-offensive-security SKILL.en.md:326
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      5. [✅/⚠️/🔴] Privilege Escalation — <brief description>
    • low Dangerous commands cmd-privilege SKILL.md:224
      Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)
      | 请求 `chmod 777` 或打开过宽权限 | 🔴 DANGER | 降低安全性 |
      tablesecurity skill

    A further 5 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 5. 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 43/100

    • 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
    • 30Running it twice. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web, git, python, node) that frontmatter does not declare
    • 100Steps. 44 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2421 tokens

    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
    • -257 emoji in the instructions: noise for the model
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 4 example trigger phrases
    • +3Description length 264: enough signal without eating the budget
    • +4Structure: 33 headings
    • +3Step-by-step instructions: 44 items
    • +4Has examples (24 code blocks)

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

    External checks

    ClawHub: suspicious
    This is a defensive installer, but it can persistently add third-party skills and its approval boundaries need careful review.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026