SKILLEMALL.ai
GitHub ↗ RU Sign in

CD crypto-scam-detector

Real-time cryptocurrency scam detection with database-first architecture. Protects users from phishing, honeypots, rug pulls, and ponzi schemes. No external API calls during checks!

modbender/skill-library-mcp Hermes author: modbender MIT 24 files · 4 scripts body ≈ 2 688 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Real-time cryptocurrency scam detection with database-first architecture.

As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerSecuritytype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
C
67/100
safety, quality, tests
Safety 60%
70
Quality 40%
62
Run on models
none yet
Process rating
D
43/100
Unfinished process
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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 26

✓ No critical or high findings

Medium and low: 26
  • medium Risky intent intent-wallet-secrets CHANGELOG.md:38
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - ✅ **Private key phishing** - Identifies seed phrase scams
  • low Secrets in code secret-high-entropy-token blockchain_detector.py:151
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    '0x09…f96',  # Ethereum
    quoted
  • low Secrets in code secret-high-entropy-token blockchain_detector.py:152
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'DYw8…SKK',  # Solana
    quoted
  • low Secrets in code secret-high-entropy-token blockchain_detector.py:153
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    '1A1z…fNa',  # Bitcoin
    quoted
  • low Secrets in code secret-high-entropy-token blockchain_detector.py:154
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'rN7n…h8F',  # XRP
    quoted
  • low Secrets in code secret-high-entropy-token blockchain_detector.py:156
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'TRX9…qzL',  # Tron
    quoted
  • low Secrets in code secret-high-entropy-token CHANGELOG.md:89
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Address `0x09…f96`:
    quoted
  • low Risky intent intent-wallet-secrets clawhub-manifest.json:109
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
    "Phishing detection - identifies seed phrase scams"
    detector
  • low Risky intent intent-wallet-secrets DATABASE_ARCHITECTURE.md:142
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    - Phishing: "private key", "seed phrase", "verify wallet"
    quoted
  • low Secrets in code secret-high-entropy-token DATABASE_ARCHITECTURE.md:151
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    All detected in the example address `0x09…f96`!
    detector
  • low Dangerous commands cmd-background-process DATABASE_ARCHITECTURE.md:248
    Starts a background / autostarted process
    sudo systemctl enable crypto-sync-worker
  • low Secrets in code secret-high-entropy-token DATABASE_ARCHITECTURE.md:261
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    ### Address: `0x09…f96`
    quoted
  • low Secrets in code secret-high-entropy-token MULTICHAIN_SUPPORT.md:38
    High-entropy token-like string (may be an id, hash or a credential)
    python3 crypto_check_db.py 0x09…f96
  • low Secrets in code secret-high-entropy-token MULTICHAIN_SUPPORT.md:41
    High-entropy token-like string (may be an id, hash or a credential)
    python3 crypto_check_db.py DYw8…SKK
  • low Secrets in code secret-high-entropy-token MULTICHAIN_SUPPORT.md:44
    High-entropy token-like string (may be an id, hash or a credential)
    python3 crypto_check_db.py rN7n…h8F
  • low Secrets in code secret-high-entropy-token MULTICHAIN_SUPPORT.md:47
    High-entropy token-like string (may be an id, hash or a credential)
    python3 crypto_check_db.py 1A1z…fNa
  • low Secrets in code secret-high-entropy-token MULTICHAIN_SUPPORT.md:64
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **Example:** `0x09…f96`
    quoted
  • low Risky intent intent-wallet-secrets README.md:120
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (documentation table row)
    | **Phishing** | Keywords: "private key", "seed phrase", "verify wallet" |
    table
  • low Secrets in code secret-high-entropy-token READY_TO_PUBLISH.md:90
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - Test address: `0x09…f96`
    detector
  • low Risky intent intent-wallet-secrets SKILL.md:165
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (documentation table row)
    | **Phishing** | Keyword analysis: "private key", "seed phrase", "verify wallet" |
    table
  • low Risky intent intent-wallet-secrets sync_worker.py:101
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    'private key', 'seed phrase', 'metamask support', 'wallet recovery',
    quoted
  • low Secrets in code secret-high-entropy-token V2.2.0_RELEASE_NOTES.md:17
    High-entropy token-like string (may be an id, hash or a credential)
    python3 crypto_check_db.py 0x09…f96  # Ethereum
  • low Secrets in code secret-high-entropy-token V2.2.0_RELEASE_NOTES.md:18
    High-entropy token-like string (may be an id, hash or a credential)
    python3 crypto_check_db.py DYw8…SKK # Solana
  • low Secrets in code secret-high-entropy-token V2.2.0_RELEASE_NOTES.md:19
    High-entropy token-like string (may be an id, hash or a credential)
    python3 crypto_check_db.py rN7n…h8F  # XRP (coming soon)
  • low Secrets in code secret-high-entropy-token V2.2.0_RELEASE_NOTES.md:78
    High-entropy token-like string (may be an id, hash or a credential)
    ./check_address.sh 0x09…f96
  • low Secrets in code secret-high-entropy-token V2.2.0_RELEASE_NOTES.md:84
    High-entropy token-like string (may be an id, hash or a credential)
    ./check_address.sh DYw8…SKK

Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 181 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "repository"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "icon"
  • note frontmatter-key unknown frontmatter key "command"

Process rating: all ten parameters 43/100

  • 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. 1 mutating operations with no state check
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 100Steps. 59 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2688 tokens
  • low 18 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)
  • +3Output format is not stated: the model decides each time
  • -250 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 181: enough signal without eating the budget
  • +4Structure: 43 headings
  • +3Step-by-step instructions: 59 items
  • +4Has examples (19 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.