SKILLEMALL.ai
GitHub ↗ RU Sign in

CC walletchan

Drive the WalletChan browser extension as a human-in-the-loop co-pilot for web3 dapps. The agent navigates the dapp UI and surfaces each transaction or signature — decoded and human-readable — inside the extension for the user to review. A scoped, user-controlled "Agent Password" unlocks ONLY the review-and-confirm UI; it cannot export private keys, reveal the seed phrase, change security settings, or disable auto-lock. Use when the user asks to connect a wallet, swap tokens, supply/deposit to DeFi, sign typed data, or check on-chain balances through a dapp. Requires Chrome with remote debugging and the WalletChan extension installed.

ClawHub Agent Skills author: Apoorv Lathey v1.0.2 MIT-0 2 files body ≈ 3 303 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Drive the WalletChan browser extension as a human-in-the-loop co-pilot for web3 dapps.

As a process C 63/100 · Has gaps — weak spots: result and completion, running it twice

ProcedureGitHubPlaywrightAI 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
C
80/100
safety, quality, tests
Safety 60%
80
Quality 40%
81
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Running it twice w 4
30
Tools and files w 18
60
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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Risky intent intent-wallet-secrets SKILL.md:3
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      description: Drive the WalletChan browser extension as a human-in-the-loop co-pilot for web3 dapps. The agent navigates the dapp UI and surfaces each transaction or signature — decoded and human-reada
    • medium Risky intent intent-wallet-secrets SKILL.md:41
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      | **Master Password** | Vault key. Decrypts private keys and seed phrases. | **User only.** Never shared with any agent, ever. | Private key export, seed phrase reveal, security settings. |
    • medium Risky intent intent-wallet-secrets SKILL.md:47
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - Revealing a seed phrase
    • medium Risky intent intent-wallet-secrets SKILL.md:94
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - Attempt to export, reveal, copy, or transmit a private key or seed phrase.

    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 "source"
    • note frontmatter-key unknown frontmatter key "extension_listing"

    Process rating: all ten parameters 63/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 60Steps. 60 steps, 4 vague phrases
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3303 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low The response is described with custom markup (3 tags): a typed call is more reliable

    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
    • +1No license
    • +2Single-language instructions
    • +3Description length 642: enough signal without eating the budget
    • +4Structure: 20 headings
    • +3Step-by-step instructions: 60 items
    • +4Has examples (0 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

    External checks

    ClawHub: suspicious
    This skill is coherent for a wallet co-pilot, but it asks users to put a wallet-related operational password into chat and grants broad browser-control access for financial actions.
    LLM: suspicious (high) · VirusTotal: · 12 Sept 2026