The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from a product brief to inform its architectural recommendations, creating a standard surface for potential indirect prompt injection.
Ingestion points: The workflow involves reading docs/product/app_brief.md to gather context on app scale and requirements.
Boundary markers: No specific delimiters or boundary markers are defined for the ingestion of the app brief content.
Capability inventory: The skill generates architectural documentation and initial project scaffolding, including folders like lib/app/ and lib/core/.
Sanitization: No explicit sanitization or filtering of the content within the app brief is mentioned before it is processed by the agent.
[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified. The skill focuses on providing best-practice architectural guidance and utilizes well-known, community-trusted Flutter packages like Riverpod, GoRouter, and Dio.

flutter-architecture