mastermind-logger

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to autonomously scan conversation history and file context and to include concrete code snippets/commands in the output, which can cause it to copy secrets (API keys, tokens, passwords) verbatim from session text or files into the saved document, creating an exfiltration risk.