code-architecture-writer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to read files with a Read tool and copy code snippets verbatim into generated documents (and to verify exact line/content), so any API keys, tokens, or passwords present in the repository would be included in outputs and thus risk exfiltration.