SKILLEMALL.ai

DB helius

Build Solana applications with Helius infrastructure. Covers transaction sending (Sender), asset/NFT queries (DAS API), real-time streaming (WebSockets, Laserstream), event pipelines (webhooks), priority fees, wallet analysis, and agent onboarding.

Not recommendedlow grade D
ClawHub Agent Skills author: Evan v1.0.0 MIT-0 12 files · 1 script body ≈ 2 664 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process B 72/100 · Nearly there — weak spots: result and completion

GeneratorInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
D
57/100
safety, quality, tests
Safety 60%
47
Quality 40%
72
Run on models
none yet
Process rating
B
72/100
Nearly there
Result and completion w 14
0
When it triggers w 12
50
Failures and branches w 10
55
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 33

✓ No critical or high findings

Medium and low: 33
  • medium Exfiltration net-credential-use references/priority-fees.md:30
    Credential used in a network call (verify the destination is the intended service)
    const response = await fetch(`https://mainnet.helius-rpc.com/?api-key=… {
  • medium Exfiltration net-credential-use references/priority-fees.md:53
    Credential used in a network call (verify the destination is the intended service)
    const response = await fetch(`https://mainnet.helius-rpc.com/?api-key=… {
  • medium Exfiltration net-credential-use references/wallet-api.md:130
    Credential used in a network call (verify the destination is the intended service)
    const identity = await fetch(`${BASE}/v1/wallet/${address}/identity?api-key=${KEY}`).then(r => r.ok ? r.json() : null);
  • medium Exfiltration net-credential-use references/wallet-api.md:131
    Credential used in a network call (verify the destination is the intended service)
    const funding = await fetch(`${BASE}/v1/wallet/${address}/funded-by?api-key=${KEY}`).then(r => r.ok ? r.json() : null);
  • medium Exfiltration net-credential-use references/wallet-api.md:132
    Credential used in a network call (verify the destination is the intended service)
    const { data: history } = await fetch(`${BASE}/v1/wallet/${address}/history?api-key=${KEY}&limit=20`).then(r => r.json());
  • low Secrets in code secret-high-entropy-token references/das.md:169
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "token_program": "Toke…5DA",
    quoted
  • low Secrets in code secret-high-entropy-token references/das.md:170
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "associated_token_address": "H7iL…ki9",
    quoted
  • low Secrets in code secret-high-entropy-token references/enhanced-transactions.md:61
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "description": "Transfer 0.1 SOL to FXvS…kuD",
    quoted
  • low Secrets in code secret-high-entropy-token references/enhanced-transactions.md:65
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "feePayer": "M2mx…F7K",
    quoted
  • low Secrets in code secret-high-entropy-token references/enhanced-transactions.md:71
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "fromUserAccount": "M2mx…F7K",
    quoted
  • low Secrets in code secret-high-entropy-token references/enhanced-transactions.md:72
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "toUserAccount": "FXvS…kuD",
    quoted
  • low Secrets in code secret-high-entropy-token references/laserstream.md:98
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    accountInclude: ["Toke…5DA"],
    quoted
  • low Secrets in code secret-high-entropy-token references/laserstream.md:159
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "owner": ["Toke…5DA"],
    quoted
  • low Secrets in code secret-high-entropy-token references/laserstream.md:244
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "account_include": ["Toke…5DA"],
    quoted
  • low Exfiltration exfil-secret-in-url references/priority-fees.md:30
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    const response = await fetch(`https://mainnet.helius-rpc.com/?api-key=… {
    placeholder
  • low Secrets in code secret-high-entropy-token references/priority-fees.md:38
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    accountKeys: ['JUP6…aV4'],
    quoted
  • low Exfiltration exfil-secret-in-url references/priority-fees.md:53
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    const response = await fetch(`https://mainnet.helius-rpc.com/?api-key=… {
    placeholder
  • low Secrets in code secret-high-entropy-token references/priority-fees.md:185
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    accountKeys: ['JUP6…aV4'],
    quoted
  • low Secrets in code secret-high-entropy-token references/priority-fees.md:193
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    account_keys: Some(vec!["JUP6…aV4".to_string()]),
    quoted
  • low Secrets in code secret-high-entropy-token references/sender.md:34
    High-entropy token-like string (may be an id, hash or a credential)
    4ACf…DEE
  • low Secrets in code secret-high-entropy-token references/sender.md:35
    High-entropy token-like string (may be an id, hash or a credential)
    D2L6…7NZ
  • low Secrets in code secret-high-entropy-token references/sender.md:36
    High-entropy token-like string (may be an id, hash or a credential)
    9bnz…Sta
  • low Secrets in code secret-high-entropy-token references/sender.md:37
    High-entropy token-like string (may be an id, hash or a credential)
    5VY9…kwn
  • low Secrets in code secret-high-entropy-token references/sender.md:38
    High-entropy token-like string (may be an id, hash or a credential)
    2nyh…YgD
  • low Secrets in code secret-high-entropy-token references/webhooks.md:121
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "feePayer": "HXsK…664",
    quoted
  • low Secrets in code secret-high-entropy-token references/webhooks.md:125
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "fromUserAccount": "HXsK…664",
    quoted
  • low Secrets in code secret-high-entropy-token references/webhooks.md:126
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "toUserAccount": "9Pej…DTF",
    quoted
  • low Secrets in code secret-high-entropy-token references/websockets.md:125
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    accountInclude: ['JUP6…aV4'],
    quoted
  • low Secrets in code secret-high-entropy-token references/websockets.md:258
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'Toke…5DA', // Token Program
    quoted
  • low Secrets in code secret-high-entropy-token references/websockets.md:335
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Jupiter swaps | `accountInclude` | `JUP6…aV4` |
    table
  • low Secrets in code secret-high-entropy-token references/websockets.md:336
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Magic Eden NFT sales | `accountInclude` | `M2mx…F7K` |
    table
  • low Secrets in code secret-high-entropy-token references/websockets.md:337
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Pump AMM data | `accountInclude` | `pAMM…XEA` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:26
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **Path B — Agentic signup:** `generateKeypair` → user funds wallet with **~0.001 SOL** for fees + **USDC** (USDC mint: `EPjF…t1v`) — **1 USDC** basic, **$49** Devel
    quoted

Files scanned: 12. 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")

Process rating: all ten parameters 72/100

  • 0Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 55Failures and branches. 1 branches
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. No external tools needed
  • 100Steps. 36 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2664 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • 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)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 248: enough signal without eating the budget
  • +4Structure: 28 headings
  • +3Step-by-step instructions: 36 items
  • +4Reference files are cited in the instructions (9 of 9)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.

External checks

ClawHub: suspicious
This Helius skill is coherent and not malicious, but it should be reviewed carefully because it can store sensitive keys and direct agents through real crypto payments, account changes, and on-chain transaction sending.
LLM: suspicious (high) · VirusTotal: · 29 May 2026