shiny-push

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt shows and encourages embedding API keys and Azure connection strings directly as string literals (e.g., Firebase apiKey, Azure SharedAccessKey) which would require the LLM to accept and output secret values verbatim, creating exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs implementing IPushDelegate handlers (OnReceived/OnEntry) that consume push payloads from third-party providers (APNs/FCM/Azure Notification Hubs) and uses notification.Data to drive navigation and actions (see SKILL.md usage examples and delegate guidance), so untrusted push content can materially influence behavior.