SKILLEMALL.ai
GitHub ↗ RU Sign in

FD polymarket-bot

Polymarket 5-minute crypto UP/DOWN market automated trading bot. AI-powered prediction using Binance technical analysis (Position, Momentum, RSI, Volume), automated betting via Polymarket CLOB API with gnosis-safe wallet mode. Use when setting up automated crypto trading on Polymarket, monitoring 5-minute BTC/ETH markets, or managing prediction market positions.

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: 0xshahai v3.3.5 70 files · 4 scripts body ≈ 1 029 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationInfrastructuretype 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
F
34/100
safety, quality, tests
Safety 60%
0
Quality 40%
84
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.
This is a copy of a skill from another catalog; the rating counts the canonical one: polymarket-bot (ClawHub)

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Secrets in code
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 If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail.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.

How to improve

  1. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
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 · 23

  • critical Secrets in code secret-telegram-bot auto_bot_v3.py:99
    Telegram bot token (quoted — discussed, not commanded)
    TELEGRAM_BOT_TOKEN = "8315…AGM…"
    quoted
  • critical Secrets in code secret-telegram-bot auto_bot_v3.py:120
    Telegram bot token (quoted — discussed, not commanded)
    TELEGRAM_BOT_TOKEN = "8315…AGM…"
    quoted
  • critical Secrets in code secret-telegram-bot monitor_bets.py:15
    Telegram bot token (quoted — discussed, not commanded)
    TELEGRAM_BOT_TOKEN = "8315…AGM…"
    quoted
  • critical Secrets in code secret-telegram-bot position_monitor.py:17
    Telegram bot token (quoted — discussed, not commanded)
    TELEGRAM_BOT_TOKEN = "8315…AGM…"
    quoted
Medium and low: 19
  • low Exfiltration exfil-webhook-url auto_bot_v3.py:101
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage"
    placeholder
  • low Exfiltration exfil-webhook-url auto_bot_v3.py:122
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage"
    placeholder
  • low Exfiltration exfil-webhook-url monitor_bets.py:33
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage"
    placeholder
  • low Secrets in code secret-high-entropy-token package-lock.json:65
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…09f+cXft…VU2/9xiCuXMA==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:75
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…bKX+KS9G…yMA/NhKJ…RGz/Q==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:136
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…Wwy+ghLE…vfU/YnxW…fdg==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:237
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…2BV+FY5ZFezP/ypmwayk68+NzzA…NFD/uUmBJuGoXw==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:255
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…vZS+VIDU…jX4+qx9M…saQ==",
    quoted
  • low Exfiltration exfil-webhook-url position_monitor.py:23
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage"
    placeholder
  • low Secrets in code secret-high-entropy-token README_AI.md:79
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - 地址: `0xb3…2A2`
    quoted
  • low Secrets in code secret-high-entropy-token REPORT.md:165
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **主钱包**：`0xb3…2A2`
    quoted
  • low Secrets in code secret-high-entropy-token REPORT.md:166
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **代理钱包（CLI）**：`0x91…0fc`
    quoted
  • low Secrets in code secret-high-entropy-token REPORT.md:168
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **充值地址（Polygon）**：`0x91…0fc`
    quoted
  • low Secrets in code secret-high-entropy-token REPORT.md:169
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **跨链桥接地址（EVM）**：`0x2A…fF6`
    quoted
  • low Dangerous commands cmd-cron-mention SKILL.md:124
    Mentions editing / listing crontab
    crontab -e
  • low Secrets in code secret-high-entropy-token wallet_backup.txt:6
    High-entropy token-like string (may be an id, hash or a credential)
    Address: 0xb3…2A2
  • low Secrets in code secret-high-entropy-token wallet_backup.txt:7
    High-entropy token-like string (may be an id, hash or a credential)
    Proxy Wallet (官网): 0xe6…1FC
  • low Dangerous commands cmd-background-process watchdog_v3.sh:13
    Starts a background / autostarted process
    nohup python3 -u auto_bot_v3.py > logs/bot_v3.log 2>&1 &
  • low Dangerous commands cmd-background-process watchdog_v3.sh:20
    Starts a background / autostarted process
    nohup python3 -u position_monitor.py > logs/position_monitor.log 2>&1 &

Files scanned: 70. 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 41/100

  • 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
  • 40Consistency. Frontmatter name (polymarket-bot) differs from the folder (polymarket-arb-bot)
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 100Steps. 102 steps
  • 100Execution cost. Instruction body is 1029 tokens
  • 100Running it twice. No mutating operations
  • low 12 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 364: enough signal without eating the budget
  • +4Structure: 33 headings
  • +3Step-by-step instructions: 102 items
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

External checks

ClawHub: suspicious
This automated trading skill has real financial authority plus under-disclosed external messaging, exposed secrets, and unsafe code paths that need review before installation.
LLM: suspicious (high) · VirusTotal: · 29 May 2026