Polymarket Macro Sentiment Divergence Trader
v1.0.1Detects macro sentiment divergence across Polymarket prediction markets. When positive-sentiment categories (sports winners, tech milestones, entertainment,...
⭐ 0· 53·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the implementation: the skill discovers markets via the Simmer client, classifies them by sentiment keywords, computes a divergence score, and places simulated or live trades using SIMMER_API_KEY. Required pieces (SIMMER_API_KEY and simmer-sdk) are proportional and expected for a trading integration.
Instruction Scope
SKILL.md and trader.py keep scope to market discovery, classification, and trading. The classifier is a simple keyword matcher and will be brittle / can misclassify (expected design tradeoff) — it does not read unrelated system files or attempt to exfiltrate data. The instructions explicitly default to paper trading and require an explicit --live flag for real trades.
Install Mechanism
No install spec in the registry; the package is instruction + a Python file that depends on simmer-sdk (declared in clawhub.json). This is low-risk and traceable to PyPI/GitHub references in SKILL.md; nothing is downloaded from arbitrary URLs or executed during install.
Credentials
Only SIMMER_API_KEY is required and is justified (used to create SimmerClient and sign trades). The skill reads tunables from environment but those are declared in clawhub.json and relate to trade limits and thresholds. No unrelated secrets or system tokens are requested.
Persistence & Privilege
autostart: false and cron: null; always: false. The skill does not force permanent inclusion or modify other skills. It re-reads tunables via apply_skill_config when available, which is appropriate for a managed skill runtime.
Scan Findings in Context
[pre-scan-injection] expected: No pre-scan injection signals were detected. This is consistent with an instruction-only/trader SDK-based skill.
Assessment
This skill appears coherent, but review before enabling live trading: 1) Keep SIMMER_API_KEY secret and only provide it to trusted runtimes; the key enables real USDC trades when --live is used. 2) The sentiment classifier is keyword-based and can misclassify markets (tune MIN_BUCKET_SIZE, thresholds, and review selected markets before placing live trades). 3) Confirm the simmer-sdk package is the official client you expect (check PyPI/GitHub links) because that library executes network operations and will hold your API key. 4) Start in paper mode, monitor behavior, and only enable --live after validating logs and risk parameters. 5) If you need higher assurance, perform an independent code review of simmer-sdk and consider running the skill in an isolated environment.Like a lobster shell, security has layers — review code before you run it.
latestvk97bgdcnq96whnfvkyze1xdqvh846r8m
License
MIT-0
Free to use, modify, and redistribute. No attribution required.