authentication

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs agents to accept user email/password or tokens and shows examples embedding passwords, refresh tokens, and API keys directly in HTTP requests/CLI commands (e.g., curl -d with password or refresh_token), which requires the LLM to handle and potentially output secret values verbatim, creating an exfiltration risk.