SKILLEMALL.ai
GitHub ↗ RU Sign in

AD skill-scanner

Scan OpenClaw skills for security vulnerabilities before installing them. Use when evaluating a new skill from ClawHub or any third-party source. Detects credential stealers, data exfiltration, malicious URLs, obfuscated code, and supply chain attacks.

modbender/skill-library-mcp Agent Skills author: modbender MIT 2 files body ≈ 993 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Scan OpenClaw skills for security vulnerabilities before installing them.

As a process D 48/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerAI and agentsSoftware developmenttype 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%
99
Quality 40%
90
Run on models
none yet
Process rating
D
48/100
Unfinished process
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Risky intent intent-offensive-security SKILL.md:74
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Environment variable access (credential harvesting)

    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 48/100

    • 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
    • 40Consistency. Frontmatter name (skill-scanner) differs from the folder (arc-skill-scanner)
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 85Steps. 42 steps, 1 vague phrases
    • 100Execution cost. Instruction body is 993 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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 252: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 42 items
    • +3Output format is stated explicitly
    • +4Has examples (8 code blocks)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.