SKILLEMALL.ai
GitHub ↗ RU Sign in

DC polymarket-oracle

Multi-strategy arbitrage and trading bot for Polymarket prediction markets. Scans ALL markets (crypto, politics, sports, economics, entertainment) for parity arbitrage, logical arbitrage, tail-end trading, market making, and latency opportunities.

Not recommendedlow grade D
modbender/skill-library-mcp Agent Skills author: modbender MIT 5 files body ≈ 2 014 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Multi-strategy arbitrage and trading bot for Polymarket prediction markets.

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorTelegramInfrastructureSoftware developmentData 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
D
51/100
safety, quality, tests
Safety 60%
38
Quality 40%
70
Run on models
none yet
Process rating
C
53/100
Has gaps
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

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.

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 18

✓ No critical or high findings

Medium and low: 18
  • medium Risky intent intent-wallet-secrets CONFIGURATION.md:90
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    **IMPORTANT:** Your wallet private key is needed **ONLY ONCE** to create Polymarket API credentials.
  • medium Dangerous commands cmd-privilege CONFIGURATION.md:141
    Privilege escalation / world-writable permissions
    sudo chmod 600 /etc/polymarket-oracle/credentials.env
  • medium Dangerous commands cmd-privilege CONFIGURATION.md:142
    Privilege escalation / world-writable permissions
    sudo chown root:root /etc/polymarket-oracle/credentials.env
  • medium Exfiltration exfil-webhook-url CONFIGURATION.md:237
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    url = f"https://api.telegram.org/bot{token}/sendMessage"
    quoted
  • medium Dangerous commands cmd-shell-rc CONFIGURATION.md:276
    Writes to a shell startup file
    cat >> ~/.bashrc << 'EOF'
  • medium Exfiltration exfil-webhook-url polymarket_oracle.py:485
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    self.api_url = f"https://api.telegram.org/bot{bot_token}/sendMessage" if bot_token else None
    quoted
  • medium Exfiltration exfil-webhook-url SKILL.md:25
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    - "https://api.telegram.org/bot*"
    quoted
  • medium Risky intent intent-wallet-secrets SKILL.md:377
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - ✅ Polygon wallet private key
  • medium Risky intent intent-wallet-secrets SYSTEMD_SETUP.md:98
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - `WALLET_PRIVATE_KEY=...` → Your Polygon wallet private key
  • medium Dangerous commands cmd-privilege SYSTEMD_SETUP.md:358
    Privilege escalation / world-writable permissions
    sudo chmod 600 /etc/polymarket-oracle/credentials.env
  • medium Dangerous commands cmd-privilege SYSTEMD_SETUP.md:359
    Privilege escalation / world-writable permissions
    sudo chown root:root /etc/polymarket-oracle/credentials.env
  • low Risky intent intent-wallet-secrets CONFIGURATION.md:88
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
    ## ⚠️ CRITICAL SECURITY - WALLET PRIVATE KEY
    detector
  • low Exfiltration exfil-webhook-url CONFIGURATION.md:217
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    https://api.telegram.org/botYOUR_TOKEN/getUpdates
    placeholder
  • low Dangerous commands cmd-background-process CONFIGURATION.md:495
    Starts a background / autostarted process
    nohup python3 polymarket_oracle.py > oracle.log 2>&1 &
  • low Dangerous commands cmd-background-process CONFIGURATION.md:622
    Starts a background / autostarted process
    sudo systemctl enable polymarket-oracle
  • low Dangerous commands cmd-background-process SYSTEMD_SETUP.md:120
    Starts a background / autostarted process
    sudo systemctl enable polymarket-oracle
  • low Dangerous commands cmd-background-process SYSTEMD_SETUP.md:223
    Starts a background / autostarted process
    sudo systemctl enable polymarket-oracle
  • low Dangerous commands cmd-background-process SYSTEMD_SETUP.md:517
    Starts a background / autostarted process
    sudo systemctl enable polymarket-oracle

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 53/100

  • 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
  • 100Tools and files. No external tools needed
  • 100Steps. 54 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2014 tokens
  • 100Running it twice. No mutating operations
  • low 11 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
  • -238 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 247: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 54 items
  • +4Has examples (17 code blocks)

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