ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

moltblock - Trust Layer for AI Agents

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

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/meshailabs/moltblock
Or

moltblock — Trust Layer for AI Agents

Description

Moltblock provides verification gating for AI-generated artifacts. It runs policy checks and optional code verification (via vitest) to catch dangerous patterns before they reach production.

What moltblock does:

  • Generates code via LLM API calls, then runs policy checks against the output
  • When --test is provided, executes vitest to verify generated code against a user-provided test file (see Security: Test Execution below)
  • Reads its own config files (moltblock.json, ~/.moltblock/moltblock.json) if present
  • API keys are read from environment variables at runtime and sent only to the configured LLM provider endpoint

When to Use

Use moltblock when the task involves:

  • High risk (always verify): Destructive operations (rm -rf, DROP TABLE), privilege escalation (sudo, chmod 777), credential/key access (.ssh/, id_rsa, .env), system modification, raw disk writes
  • Medium risk (verify when uncertain): Network requests (curl, wget, fetch), file writes, database modifications, subprocess spawning, dynamic code evaluation
  • Low risk (skip verification): Simple text responses, math, reading public information, code that doesn't touch the filesystem or network

Tool: moltblock

Verify a task before execution.

Usage

npx [email protected] "<task description>" --provider <provider> --json

Parameters

ParameterRequiredDescription
taskYesThe task description to verify
--providerNoLLM provider: openai, google, zai, local (auto-detected from env)
--modelNoModel override
--testNoPath to test file (for code verification)
--jsonNoOutput structured JSON result

Environment Variables

Moltblock auto-detects the LLM provider from whichever API key is set. If no key is set, it falls back to a local LLM at localhost:1234. Set one of these for a cloud provider:

  • OPENAI_API_KEY — OpenAI (primary)
  • ANTHROPIC_API_KEY — Anthropic/Claude (optional)
  • GOOGLE_API_KEY — Google/Gemini (optional)
  • ZAI_API_KEY — ZAI (optional)

Example

# Verify a task
npx [email protected] "implement a function that validates email addresses" --json

# Verify code with tests
npx [email protected] "implement a markdown-to-html converter" --test ./tests/markdown.test.ts --json

Output (JSON mode)

{
  "verification_passed": true,
  "verification_evidence": "All policy rules passed.",
  "authoritative_artifact": "...",
  "draft": "...",
  "critique": "...",
  "final_candidate": "..."
}

Installation

Use directly with npx (recommended, no install needed):

npx [email protected] "your task" --json

Or install globally:

npm install -g [email protected]

Configuration

No configuration file is required.

Metadata

Stars1401
Views1
Updated2026-02-24
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-meshailabs-moltblock": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.