SKILLEMALL.ai
GitHub ↗ RU Sign in

BC autonomous-wallet

Self-healing crypto wallet for AI agents with intent-based execution and social recovery | AI 代理的自我修复加密钱包，支持意图执行和社交恢复

ClawHub Agent Skills author: Justin Liu v1.0.0 MIT-0 3 files body ≈ 3 502 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

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

ProcedureAI and agentsInfrastructuretype 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
76/100
safety, quality, tests
Safety 60%
82
Quality 40%
66
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 readme.md:92
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    export MNEMONIC="word1 word2..."  # Or mnemonic phrase
  • medium Risky intent intent-wallet-secrets skill.md:11
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    description: 12/24-word recovery phrase (alternative to private key) | 12/24 词助记词（私钥的替代方案）
  • medium Risky intent intent-wallet-secrets skill.md:54
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - **Local wallet**: Private key or mnemonic phrase (stored locally)
  • low Risky intent intent-wallet-secrets skill.md:141
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    autonomous-wallet import --mnemonic "your twelve word mnemonic phrase..."
    quoted
  • low Secrets in code secret-high-entropy-token skill.md:152
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    autonomous-wallet execute "Send 0.1 ETH to 0x74…bEb"
    quoted
  • low Secrets in code secret-high-entropy-token skill.md:544
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    autonomous-wallet execute "发送 0.1 ETH 到 0x74…bEb"
    quoted

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "requires"

Process rating: all ten parameters 63/100

  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. No external tools needed
  • 100Steps. 90 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3502 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 117: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -250 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 71 headings
  • +3Step-by-step instructions: 90 items
  • +4Has examples (30 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
This appears to be a real crypto-wallet skill, but it gives an agent high-impact control over funds with insufficiently prominent safeguards around keys and irreversible transactions.
LLM: suspicious (high) · VirusTotal: · 29 May 2026