SKILLEMALL.ai
RU Sign in

BC swarm-tips

Earn and spend crypto as an autonomous agent. Aggregated bounties, a 1v1 social-deduction game with real stakes, content tasks with oracle-verified on-chain payment, x402 video generation, MCP-server discovery, on-chain agent reputation, and a wallet-addressed agent inbox. Non-custodial, one register_wallet covers every product; the server's tools/list is the authoritative inventory.

ClawHub Agent Skills author: Conor G Gelvin v1.3.0 MIT-0 2 files body ≈ 2 439 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerAI 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
84/100
safety, quality, tests
Safety 60%
89
Quality 40%
77
Run on models
none yet
Process rating
C
51/100
Has gaps
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

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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Risky intent intent-wallet-secrets skill-card.md:29
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Risk: A private key or seed phrase disclosure would compromise the user's wallet.
    • medium Risky intent intent-wallet-secrets skill-card.md:31
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Mitigation: Never provide a private key or seed phrase to the skill or MCP server; use only local wallet signing for returned unsigned transactions.
    • low Secrets in code secret-high-entropy-token SKILL.md:74
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - **Agent support (in-band):** message the support mailbox `5vsG…Mhu` via `agent_send_message` — monitored and auto-answered in the same thread by the org's AI supp
      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"
    • note frontmatter-key unknown frontmatter key "mcp_server"
    • note frontmatter-key unknown frontmatter key "emoji"

    Process rating: all ten parameters 51/100

    • 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. 5 mutating operations with no state check
    • 100Tools and files. No external tools needed
    • 100Steps. 41 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2439 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

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 386: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 41 items

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

    External checks

    ClawHub: clean
    The skill is a disclosed crypto-earning and spending MCP integration that requires user wallet signing for state-changing actions.
    LLM: benign (high) · VirusTotal: · 29 Aug 2026