The Agent Skills Directory

[SAFE]: The skill consists of architectural guidelines and standard Dart code snippets for Flutter development. No evidence of malicious intent, obfuscation, or unauthorized data access was found.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided Flutter source code to recommend theming improvements. This creates a potential surface for indirect prompt injection if the user code contains malicious instructions embedded in comments or string literals. The risk is considered negligible given the skill's purpose and restricted tool access.
Ingestion points: User-provided widget code, ThemeData configurations, and project files (via Read, Glob, and Grep tools).
Boundary markers: No specific delimiters or safety instructions are defined to separate user code from agent instructions.
Capability inventory: Read, Glob, Grep (File system inspection only). No file-writing or network capabilities are requested.
Sanitization: No input sanitization or validation of the ingested source code is implemented.

material-theming