t2000-earn

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the user/agent to pass an API key directly via a command-line argument (t2 connect hermes --key sk-…), which is an insecure credential handling pattern.

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads job board listings, specifications, and buyer deliveries from the t2000 marketplace, which are authored by external marketplace buyers.

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

• Direct money access detected (high risk: 1.00). The skill documentation explicitly utilizes a local crypto wallet (t2 wallet) and specific CLI commands (t2 job claim, t2 job batch-claim) to interact with blockchain-based marketplace escrow and earn USDC, falling under the crypto/blockchain and market transaction execution capability.