SKILLEMALL.ai
GitHub ↗ RU Sign in

CB kryptogo-meme-trader

[DEPRECATED 2026-05-04] Analyze and trade meme coins using KryptoGO's on-chain cluster analysis platform. NOTE: The kg-xyz analysis backend (wallet-data.kryptogo.app) is shutting down on 2026-05-04 — cluster analysis, wallet labels, signal dashboard, and DCA/limit order tools will stop working after that date. Swap execution via the OKX DEX aggregator continues to function.

ClawHub Agent Skills author: Harry Chen v2.6.0 MIT-0 20 files · 5 scripts body ≈ 3 943 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 65/100 · Nearly there — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerSoftware developmentInfrastructureData and analyticstype 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
67/100
safety, quality, tests
Safety 60%
58
Quality 40%
81
Run on models
none yet
Process rating
B
65/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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 · 38

    ✓ No critical or high findings

    Medium and low: 38
    • medium Risky intent intent-wallet-secrets skill-card.md:44
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      **Other Properties Related to Output:** [Requires a KryptoGO API key, a Solana wallet private key and address, Python tooling, network access to wallet-data.kryptogo.app for degraded analysis paths, a
    • low Secrets in code secret-high-entropy-token examples/trading-workflow.py:53
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      SOL_MINT = "So11…112"
      fixturequoted
    • low Secrets in code secret-high-entropy-token references/api-reference.md:12
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - Wrapped SOL mint: `So11…112`
      quoted
    • low Secrets in code secret-high-entropy-token references/api-reference.md:686
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "input_mint": "So11…112",
      quoted
    • low Secrets in code secret-high-entropy-token references/api-reference.md:690
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "wallet_address": "EQ7C…AUN"
      quoted
    • low Secrets in code secret-high-entropy-token references/api-reference.md:716
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "fee_payer": "EQ7C…AUN",
      quoted
    • low Secrets in code secret-high-entropy-token references/api-reference.md:717
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "signers": ["EQ7C…AUN"]
      quoted
    • low Exfiltration read-dotenv references/autonomous-trading.md:61
      Reads a .env file
      source ~/.openclaw/workspace/.env && bash scripts/cron-examples.sh setup-default
    • low Exfiltration read-dotenv references/autonomous-trading.md:69
      Reads a .env file
      source ~/.openclaw/workspace/.env && bash scripts/cron-examples.sh setup-autonomous
    • low Exfiltration read-dotenv references/autonomous-trading.md:117
      Reads a .env file
      source ~/.openclaw/workspace/.env && bash scripts/cron-examples.sh setup-default
    • low Secrets in code secret-high-entropy-token references/autonomous-trading.md:197
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "token_mint": "DezX…263",
      quoted
    • low Exfiltration read-dotenv scripts/analysis.sh:13
      Reads a .env file (code comment)
      # Credentials must be pre-loaded in the environment (source ~/.openclaw/workspace/.env)
      comment
    • low Exfiltration read-dotenv scripts/analysis.sh:15
      Reads a .env file (detector / deny-list definition)
      echo "ERROR: Run 'source ~/.openclaw/workspace/.env' before running this script."
      detector
    • low Exfiltration read-dotenv scripts/cron_monitor.py:21
      Reads a .env file (code comment)
      # Credentials must be pre-loaded in the environment (source ~/.openclaw/workspace/.env)
      comment
    • low Exfiltration read-dotenv scripts/cron_monitor.py:24
      Reads a .env file (detector / deny-list definition)
      print("ERROR: Missing KRYPTOGO_API_KEY or SOLANA_WALLET_ADDRESS. Run 'source ~/.openclaw/workspace/.env' first.")
      detector
    • low Secrets in code secret-high-entropy-token scripts/cron_monitor.py:34
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      SOL_MINT = "So11…112"
      quoted
    • low Exfiltration read-dotenv scripts/cron_scan.py:23
      Reads a .env file (code comment; documentation of a security skill)
      # Credentials must be pre-loaded in the environment (source ~/.openclaw/workspace/.env)
      commentsecurity skill
    • low Secrets in code secret-high-entropy-token scripts/cron_scan.py:44
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      SOL_MINT = "So11…112"
      quoted
    • low Exfiltration read-dotenv scripts/cron-examples.sh:26
      Reads a .env file (detector / deny-list definition; test fixture / example file)
      --message "Run the monitoring script: 'source ~/.openclaw/workspace/.env && python3 skills/kryptogo-meme-trader/scripts/monitor.py'. Check portfolio for stop-loss or take-profit conditions. Report tri
      detectorfixture
    • low Exfiltration read-dotenv scripts/cron-examples.sh:73
      Reads a .env file (detector / deny-list definition; test fixture / example file)
      --message "Run the monitoring script: 'source ~/.openclaw/workspace/.env && python3 skills/kryptogo-meme-trader/scripts/monitor.py'. Report the output."
      detectorfixture
    • low Exfiltration read-dotenv scripts/monitor.py:8
      Reads a .env file (code comment)
      # Credentials must be pre-loaded in the environment (source ~/.openclaw/workspace/.env)
      comment
    • low Exfiltration read-dotenv scripts/monitor.py:14
      Reads a .env file (detector / deny-list definition)
      print("Run 'source ~/.openclaw/workspace/.env' before running this script.")
      detector
    • low Exfiltration read-dotenv scripts/portfolio.sh:12
      Reads a .env file (code comment)
      # Credentials must be pre-loaded in the environment (source ~/.openclaw/workspace/.env)
      comment
    • low Exfiltration read-dotenv scripts/portfolio.sh:14
      Reads a .env file (detector / deny-list definition)
      echo "ERROR: Run 'source ~/.openclaw/workspace/.env' before running this script."
      detector
    • low Risky intent intent-wallet-secrets scripts/swap.py:26
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      SOLANA_PRIVATE_KEY     - Agent wallet private key (base58, never sent to server)
      quoted
    • low Exfiltration read-dotenv scripts/swap.py:30
      Reads a .env file (detector / deny-list definition; security demo / example)
      the environment by the caller (e.g., `source ~/.openclaw/workspace/.env`).
      detectordemo
    • low Secrets in code secret-high-entropy-token scripts/swap.py:59
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      SOL_MINT = "So11…112"
      quoted
    • low Exfiltration read-dotenv scripts/swap.py:62
      Reads a .env file (detector / deny-list definition)
      sys.exit("ERROR: Missing required env vars. Run 'source ~/.openclaw/workspace/.env' before running this script.")
      detector
    • low Exfiltration read-dotenv scripts/test-api.sh:11
      Reads a .env file (code comment; test fixture / example file)
      # Credentials must be pre-loaded in the environment (source ~/.openclaw/workspace/.env)
      commentfixture
    • low Exfiltration read-dotenv scripts/test-api.sh:13
      Reads a .env file (detector / deny-list definition; test fixture / example file)
      echo "ERROR: Run 'source ~/.openclaw/workspace/.env' before running this script."
      detectorfixture
    • low Exfiltration read-dotenv scripts/trending.sh:13
      Reads a .env file (code comment)
      # Credentials must be pre-loaded in the environment (source ~/.openclaw/workspace/.env)
      comment
    • low Exfiltration read-dotenv scripts/trending.sh:15
      Reads a .env file (detector / deny-list definition)
      echo "ERROR: Run 'source ~/.openclaw/workspace/.env' before running this script."
      detector
    • low Exfiltration read-dotenv SKILL.md:122
      Reads a .env file (detector / deny-list definition)
      - Runtime scripts do NOT read `.env` directly — all credentials are accessed via environment variables only, which must be pre-loaded by the caller (`source ~/.openclaw/workspace/.env`)
      detector
    • low Exfiltration read-dotenv SKILL.md:147
      Reads a .env file
      source ~/.openclaw/workspace/.env
    • low Exfiltration read-dotenv SKILL.md:200
      Reads a .env file (detector / deny-list definition)
      Runtime scripts in this skill do NOT read `.env` files directly. All credentials are accessed via environment variables only, which must be pre-loaded by the caller (`source ~/.openclaw/workspace/.env
      detector
    • low Exfiltration read-dotenv SKILL.md:212
      Reads a .env file
      source ~/.openclaw/workspace/.env && bash scripts/cron-examples.sh setup-default
    • low Exfiltration read-dotenv SKILL.md:215
      Reads a .env file
      source ~/.openclaw/workspace/.env && bash scripts/cron-examples.sh setup-autonomous

    A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"
    • note frontmatter-key unknown frontmatter key "docs"
    • note frontmatter-key unknown frontmatter key "platform"
    • note frontmatter-key unknown frontmatter key "api_base"

    Process rating: all ten parameters 65/100

    • 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
    • 100Tools and files. No external tools needed
    • 100Steps. 33 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3943 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
    • low 17 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (6 tags): a typed call is more reliable

    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
    • -214 emoji in the instructions: noise for the model
    • -33 of 10 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 376: enough signal without eating the budget
    • +4Structure: 36 headings
    • +3Step-by-step instructions: 33 items
    • +4Has examples (7 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)
    • +1License stated

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

    External checks

    ClawHub: suspicious
    This is a disclosed crypto trading skill, but its default monitoring path can execute live sells despite documentation saying supervised mode only notifies the user.
    LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026