deepseek-claude-code-worker-mcp

SUSPICIOUS: the skill's core purpose is coherent, but its trust model is weak. The main concern is executing MCP code directly from a personal GitHub repository that does not match the skill publisher, while also providing API credentials and code-execution capability. Data flow to DeepSeek appears purpose-consistent, so this is not confirmed malware, but the install and credential-forwarding footprint is too risky to rate benign.