claude-md-progressive-disclosurer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to extract and list "Credentials/passwords/API keys" in verification checklists and even includes test queries like "Show me the credentials for [system]", which requires the model to handle and potentially output secret values verbatim.