SKILLEMALL.ai
GitHub ↗ RU Sign in

BF carbium

Build on Solana with Carbium infrastructure — bare-metal RPC, Standard WebSocket pubsub, gRPC Full Block streaming (~22ms), DEX aggregation via CQ1 engine (sub-ms quotes), gasless swaps, and MEV-protected execution via Jito bundling. Drop-in replacement for Helius, QuickNode, Triton, or Jupiter Swap API.

ClawHub Agent Skills author: Ukkometa v1.0.3 MIT-0 17 files body ≈ 8 796 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 41/100 · Will not run — References files that are not bundled: examples/pump-snipe/example.ts

GeneratorInfrastructuretype 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%
79
Quality 40%
71
Run on models
none yet
Process rating
F
41/100
Will not run
References files that are not bundled: examples/pump-snipe/example.ts
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
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 · 21

✓ No critical or high findings

Medium and low: 21
  • low Secrets in code secret-high-entropy-token examples/gasless-swap/README.md:26
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const SOL_MINT = "So11…112";
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/gasless-swap/README.md:27
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const USDC_MINT = "EPjF…t1v";
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/grpc-stream/README.md:17
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const PROGRAM_ID = "6EF8…F6P"; // Pump.fun
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/pump-snipe/README.md:34
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const PUMP_PROGRAM = new PublicKey("6EF8…F6P");
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/pump-snipe/README.md:35
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const PUMP_GLOBAL = new PublicKey("4wTV…njf");
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/pump-snipe/README.md:36
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const PUMP_FEE_RECIPIENT = new PublicKey("CebN…9iM");
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/pump-snipe/README.md:37
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const PUMP_EVENT_AUTH = new PublicKey("Ce6T…9F1");
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/swap-bundle/README.md:77
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const SOL = "So11…112";
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/swap-bundle/README.md:78
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const USDC = "EPjF…t1v";
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/swap-quote/README.md:24
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const SOL_MINT = "So11…112";
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/swap-quote/README.md:25
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const USDC_MINT = "EPjF…t1v";
    fixturequoted
  • low Secrets in code secret-high-entropy-token SKILL.md:379
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const PROGRAM_ID = "6EF8…F6P";
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:455
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    PROGRAM_ID = "6EF8…F6P"
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:593
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "src_mint": "So11…112",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:594
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "dst_mint": "EPjF…t1v",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:630
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    url.searchParams.set("src_mint", "So11…112");
    quoted
  • low Exfiltration net-credential-use SKILL.md:806
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    const res = await fetch(`https://rpc.carbium.io/?apiKey=… {
    vendor-host
  • low Exfiltration exfil-secret-in-url templates/carbium-setup.ts:24
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    `https://rpc.carbium.io/?apiKey=…
    placeholder
  • low Secrets in code secret-high-entropy-token templates/carbium-setup.ts:79
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    SOL: "So11…112",
    quoted
  • low Secrets in code secret-high-entropy-token templates/carbium-setup.ts:80
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDC: "EPjF…t1v",
    quoted
  • low Secrets in code secret-high-entropy-token templates/carbium-setup.ts:81
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDT: "Es9v…NYB",
    quoted

Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 8796 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: examples/pump-snipe/example.ts
  • note frontmatter-key unknown frontmatter key "creator"

Process rating: all ten parameters 41/100

Will not run. References files that are not bundled: examples/pump-snipe/example.ts
  • 0Tools and files. 1 referenced file(s) missing: examples/pump-snipe/example.ts
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 12 mutating operations with no state check
  • 40Execution cost. Instruction body is 8796 tokens: crowds the task out of the window
  • 100Steps. 32 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 17 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 305: enough signal without eating the budget
  • +4Structure: 73 headings
  • +3Step-by-step instructions: 32 items
  • +4Has examples (34 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.

External checks

ClawHub: suspicious
The skill matches its Solana trading purpose, but it includes live fund-moving examples with insufficient safeguards around signing and submitting transactions.
LLM: suspicious (high) · VirusTotal: benign · 28 May 2026