debugging

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires pasting module/context verbatim into subagent prompts and instructs agents to report findings and file snippets back to the user, which can force the model to ingest and then output secret values (API keys, tokens, .env contents) if they exist in the code or config files.