openclawby-skills

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow incorporates social media search tools (x_search, facebook_search) which ingest outsider-authored social posts and content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and executing remote code and zip archives from an unverified third-party domain (openclawby.com and github.com/openclawby), constituting an operational high-risk dependency.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly contains trade execution capabilities and connectors for crypto exchanges (Binance, OKX, Bitget, Polymarket, GMGN) with functions to place market orders, limit orders, and prediction market bets directly via API or CLI. This falls under Direct Financial Execution (Market Orders / Crypto Wallets / Swaps).