SKILLEMALL.ai
GitHub ↗ RU Sign in

CF solana-funding-arb

Solana perpetual DEX funding rate arbitrage - scanner and auto-trader. Compares funding rates across Drift and Flash Trade to find and execute cross-DEX arbitrage opportunities. Use when analyzing Solana perp funding rates, finding funding arbitrage, setting up delta-neutral strategies, or running automated funding collection. Includes Monte Carlo simulation, backtesting, and full auto-trading capabilities.

ClawHub Agent Skills author: chillax4life v1.0.0 30 files body ≈ 1 084 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 28/100 · Will not run — References files that are not bundled: references/api.md

AnalyzerData and analyticsSoftware developmenttype 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
70/100
safety, quality, tests
Safety 60%
65
Quality 40%
78
Run on models
none yet
Process rating
F
28/100
Will not run
References files that are not bundled: references/api.md
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
This is a copy of a skill from another catalog; the rating counts the canonical one: solana-funding-arb (ClawHub)

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Secrets in code 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 files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

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. 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 · 19

✓ No critical or high findings

Medium and low: 19
  • medium Secrets in code secret-labelled-token AGENTS(2).md:151
    Labelled token / key literal (vendor format unknown — verify it is not a live credential)
    https://mainnet.helius-rpc.com/?api-key=…
  • medium Risky intent intent-wallet-secrets Gemini-Unwrapping Wrapped SOL Funds.md:526
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    *   **The "Sweeper Bot" (Trap Wallet):** If you received the private key or seed phrase for this wallet from someone else (e.g., a "stranger" on Telegram or a site offering "free money"), it is a trap
  • medium Risky intent intent-wallet-secrets Gemini-Unwrapping Wrapped SOL Funds.md:547
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    **Would you like me to look up your wallet address on a block explorer to see if there is a bot actively "sweeping" your transactions?** (Just provide the wallet address, NEVER your private key or see
  • medium Risky intent intent-wallet-secrets Gemini-Unwrapping Wrapped SOL Funds.md:1193
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    The reason it feels like "bullshit" is because the way they did it is **counter-intuitive**. Even if your seed phrase never left your head and your home network is a fortress, they didn't need your ke
  • low Exfiltration read-dotenv AGENTS(1).md:105
    Reads a .env file (documentation of a security skill)
    cp .env.example .env
    security skill
  • low Secrets in code secret-password-literal AGENTS(2).md:151
    Hard-coded password / key literal (may be an example)
    https://mainnet.helius-rpc.com/?api-key=…
  • low Exfiltration read-dotenv Gemini-Docker Deployment Pipeline Explained.md:87
    Reads a .env file (Dockerfile instruction (build context, not runtime exfiltration); documentation of a security skill)
    COPY .env.production ./.env
    Dockerfilesecurity skill
  • low Secrets in code secret-high-entropy-token Gemini-Unwrapping Wrapped SOL Funds.md:7
    High-entropy token-like string (may be an id, hash or a credential)
    how in the fuck do i burn So11…112 so i can unlock my funds?
  • low Secrets in code secret-high-entropy-token Gemini-Unwrapping Wrapped SOL Funds.md:12
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    I can see the frustration here—dealing with "stuck" funds on-chain is a massive headache. However, I have to be very direct with you: **the address `So11…112` is the
    quoted
  • low Secrets in code secret-high-entropy-token Gemini-Unwrapping Wrapped SOL Funds.md:41
    High-entropy token-like string (may be an id, hash or a credential)
    how in the fuck do i burn So11…112 so i can unlock my funds?
  • low Secrets in code secret-high-entropy-token Gemini-Unwrapping Wrapped SOL Funds.md:62
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    The address `So11…112` is **Wrapped SOL (wSOL)**. It is not a scam token, and "burning" it will destroy your money.
    quoted
  • low Secrets in code secret-high-entropy-token Gemini-Unwrapping Wrapped SOL Funds.md:97
    High-entropy token-like string (may be an id, hash or a credential)
    how in the fuck do i burn So11…112 so i can unlock my funds?
  • low Risky intent intent-wallet-secrets Gemini-Unwrapping Wrapped SOL Funds.md:213
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    **Did someone on Telegram, Discord, or Twitter give you a "private key" or "seed phrase" to a wallet that they claimed had thousands of dollars in it?** If so, I can explain exactly how that specific
    quoted
  • low Risky intent intent-wallet-secrets Gemini-Unwrapping Wrapped SOL Funds.md:377
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    **Did someone send you a "private key" or "seed phrase" to this wallet and tell you there was money in it?** If yes, that is a known "Honey Pot" scam, and any money you send there will be instantly st
    quoted
  • low Obfuscation obf-base64-blob Gemini-Unwrapping Wrapped SOL Funds.md:1010
    Long base64-looking blob (documentation of a security skill)
    [Orb Markets](https://orbmarkets.io/tx/5XPZ…kBX?tab=…)
    security skill
  • low Obfuscation obf-base64-blob Gemini-Unwrapping Wrapped SOL Funds.md:1039
    Long base64-looking blob (documentation of a security skill)
    [Failed](https://orbmarkets.io/tx/5XPZ…kBX?tab=…)
    security skill
  • low Exfiltration read-dotenv README.md:91
    Reads a .env file (documentation of a security skill)
    cp .env.example .env
    security skill
  • low Dangerous commands cmd-cron-mention SKILL.md:107
    Mentions editing / listing crontab (documentation of a security skill)
    # Add to crontab -e
    security skill
  • low Exfiltration read-dotenv USER_GUIDE.md:51
    Reads a .env file (documentation of a security skill)
    cp .env.example .env
    security skill

Files scanned: 30. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/api.md

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: references/api.md
  • 0Tools and files. 1 referenced file(s) missing: references/api.md
  • 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
  • 40Consistency. Frontmatter name (solana-funding-arb) differs from the folder (gemini-chat-md-converts)
  • 100Steps. 20 steps
  • 100Execution cost. Instruction body is 1084 tokens
  • low 13 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 410: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
This skill is advertised as a Solana arbitrage tool, but the bundle includes unrelated high-risk trading, browser-stealth, and remote-command instructions that users should review carefully.
LLM: suspicious (high) · VirusTotal: malicious · 28 May 2026