SKILLEMALL.ai
GitHub ↗ RU Sign in

BC swimmer-stock-trading

Discover Swimmer Finance Solana stock-token routes and balances, then submit a custodial order instruction by irreversibly transferring USDC or a trusted stock token to the fixed operator recipient with a public memo. Use for pool discovery, tradability checks, optional quotes, balance checks, market or limit order preparation, explicit risk confirmation, local signing, submission, and settlement-status checks. This is not an atomic on-chain swap and does not guarantee execution, consideration, cancellation, or refund.

ClawHub Agent Skills author: Kronus91 v1.0.2 MIT-0 14 files body ≈ 1 106 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Discover Swimmer Finance Solana stock-token routes and balances, then submit a custodial order instruction by irreversibly transferring USDC or a trusted…

As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureInfrastructureCommercetype 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
82/100
safety, quality, tests
Safety 60%
83
Quality 40%
81
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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

    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 · 9

    ✓ No critical or high findings

    Medium and low: 9
    • medium Risky intent intent-wallet-secrets references/keypair-setup.md:23
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - `private_key`: a new dedicated base…ded 64-byte Solana keypair, never a seed phrase or primary wallet.
    • medium Risky intent intent-wallet-secrets SKILL.md:25
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - Never ask for or display a seed phrase, private key, wallet export, or config contents. If a secret appears in chat or output, tell the user to treat it as compromised and move funds from a separate
    • low Secrets in code secret-high-entropy-token references/custody-and-settlement.md:6
      High-entropy token-like string (may be an id, hash or a credential)
      Cdnw…2cf
    • low Secrets in code secret-high-entropy-token references/keypair-setup.md:38
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "EPjF…t1v": "25000000"
      quoted
    • low Secrets in code secret-high-entropy-token references/wallet-submission.md:11
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "offer_mint": "EPjF…t1v",
      quoted
    • low Secrets in code secret-high-entropy-token scripts/solana_sign_send.py:32
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      TOKEN_PROGRAM_ID = Pubkey.from_string("Toke…5DA")
      quoted
    • low Secrets in code secret-high-entropy-token scripts/solana_sign_send.py:33
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      MEMO_PROGRAM_ID = Pubkey.from_string("Memo…cHr")
      quoted
    • low Secrets in code secret-high-entropy-token scripts/solana_sign_send.py:34
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      SOLANA_USDC_MINT = Pubkey.from_string("EPjF…t1v")
      quoted
    • low Secrets in code secret-high-entropy-token scripts/solana_sign_send.py:36
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "Cdnw…2cf"
      quoted

    Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 54/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 4 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 100Steps. 16 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1106 tokens
    • 100Progress reporting. Reports progress

    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
    • -32 of 2 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 524: enough signal without eating the budget
    • +4Structure: 4 headings
    • +3Step-by-step instructions: 16 items
    • +4Reference files are cited in the instructions (5 of 5)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

    External checks

    ClawHub: clean
    This is a disclosed, scoped trading skill, but using it can irreversibly send real tokens to a custodian.
    LLM: benign (high) · VirusTotal: · 2 Sept 2026