ios-interaction-primitives-design

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill mandates quoting the user's actual code in "Before" and producing "After" with exact API calls and exact values (e.g., tokens/authenticationToken examples and push-token upload), which forces the model to reproduce any secrets present in user-provided code or configs verbatim, creating an exfiltration risk.