SKILLEMALL.ai
GitHub ↗ RU Sign in

AD moltblock - Trust Layer for AI Agents

Verification gating for AI-generated artifacts. Policy checks to catch dangerous patterns before execution.

ClawHub Agent Skills author: meshailabs v0.11.9 MIT-0 2 files body ≈ 1 103 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Verification gating for AI-generated artifacts.

As a process D 47/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerGitHubSoftware developmentAI and agentstype 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
90/100
safety, quality, tests
Safety 60%
98
Quality 40%
77
Run on models
none yet
Process rating
D
47/100
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Dangerous commands cmd-privilege SKILL.md:45
      Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
      - **High risk** (always verify): Destructive operations (`rm -rf`, `DROP TABLE`), privilege escalation (`sudo`, `chmod 777`), credential/key access (`.ssh/`, `id_rsa`, `.env`), system modification, ra
      quoted
    • low Risky intent intent-offensive-security SKILL.md:45
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **High risk** (always verify): Destructive operations (`rm -rf`, `DROP TABLE`), privilege escalation (`sudo`, `chmod 777`), credential/key access (`.ssh/`, `id_rsa`, `.env`), system modification, ra

    Files scanned: 2. 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)
    • note frontmatter-key unknown frontmatter key "homepage"
    • note frontmatter-key unknown frontmatter key "repository"

    Process rating: all ten parameters 47/100

    • 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
    • 30Running it twice. 1 mutating operations with no state check
    • 40Consistency. Frontmatter name (moltblock - Trust Layer for AI Agents) differs from the folder (moltblock)
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 100Steps. 15 steps
    • 100Execution cost. Instruction body is 1103 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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)
    • +3Description length 107: 120–800 characters recommended
    • +1No license
    • +2Single-language instructions
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 15 items
    • +3Output format is stated explicitly
    • +4Has examples (6 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

    External checks

    ClawHub: clean
    The skill is coherent as an LLM-backed verification tool, with standard but real npm/package and API-key handling risks users should understand.
    LLM: benign (medium) · VirusTotal: · 10 Sept 2026