Prediction Market Arbiter

Cross-platform divergence scanner comparing Kalshi and Polymarket prices on identical events. Fuzzy title matching across 1000+ markets per run, configurable...

This skill appears to implement a legitimate Kalshi↔Polymarket divergence scanner, but there are metadata/instruction mismatches you should address before use: - The SKILL.md and script read a per-user config (~/.openclaw/config.yaml) and a Kalshi private key PEM file, but the registry metadata does not declare any required config paths or credentials. Treat the private_key_file as highly sensitive: do not point it at unrelated keys (SSH, cloud credentials, etc.). - Verify where the script will write cache/JSON files (current working dir or a logged path) and run it in an isolated environment (VM/container) if you are unsure. - Inspect the kalshi-python package (version pinned in requirements.txt) yourself, and install dependencies in a virtualenv rather than globally. - Consider adding the Kalshi credentials via a dedicated Kalshi key (not reuse of other private keys) and confirm the key format before supplying the path. - Because the skill metadata omits the config file requirement, ask the publisher (or update metadata locally) to declare the required config path and the sensitive file access so you can assess it fully. If you cannot verify these items, treat the skill as untrusted and avoid supplying high-value secrets or system-wide keys.

Type: OpenClaw Skill Name: prediction-market-arbiter Version: 1.1.5 The skill bundle is a legitimate tool for scanning price divergences between Kalshi and Polymarket. The code in `scripts/arbiter.py` correctly implements the described fuzzy matching logic and interacts only with official API endpoints (kalshi.com and polymarket.com). While it handles sensitive Kalshi API credentials, it does so locally as required for authentication without any signs of exfiltration or unauthorized execution.