SKILLEMALL.ai
GitHub ↗ RU Sign in

BC drain-mcp

MCP server for the Handshake58 AI marketplace. Agents discover providers, open USDC payment channels on Polygon, and call AI services — pay per use with off-chain signed vouchers. No API keys, no subscriptions.

ClawHub Agent Skills author: Artur Markus v1.8.0 2 files body ≈ 2 306 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 59/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches

IntegrationAI 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
B
86/100
safety, quality, tests
Safety 60%
86
Quality 40%
87
Run on models
none yet
Process rating
C
59/100
Has gaps
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Risky intent medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • medium Risky intent intent-wallet-secrets skill-card.md:20
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Risk: The external MCP package can use a wallet private key to authorize spending from the configured Polygon wallet. <br>
    • medium Risky intent intent-wallet-secrets skill-card.md:21
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Mitigation: Use a fresh low-balance wallet dedicated to this skill and never provide a main wallet or seed phrase. <br>
    • low Secrets in code secret-high-entropy-token SKILL.md:137
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      await usdc.approve('0x1C…e64', amount);
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:179
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      to: '0x1C…e64',
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:230
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - **Handshake58 Channel**: `0x1C…e64`
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:231
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - **USDC**: `0x3c…359`
      quoted

    Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 59/100

    • 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. 7 mutating operations with no state check
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 28 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2306 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 12 top-level sections: this looks like several domains in one skill

    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)
    • +2Single-language instructions
    • +3Description length 210: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 28 items
    • +3Output format is stated explicitly
    • +4Has examples (9 code blocks)
    • +1License stated

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

    External checks

    ClawHub: suspicious
    The skill is transparent about its crypto-payment purpose, but it gives an external MCP package access to a wallet private key that can spend funds.
    LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026