validate-output

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs constructing and executing shell commands that embed the user's content verbatim (e.g., --text "{content}") and reads local brand files, so if those inputs contain API keys/passwords/tokens the agent would be required to include them directly in generated commands or outputs, risking secret exfiltration.