miro-code-to-board-architecture

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly requires embedding "offending" code snippets and diffs (via code_widget_create) and to report security flows touching "crypto keys, secrets, or session material" without instructing redaction, which creates a high likelihood the LLM will include secret values verbatim in output.