The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's workflows for reviewing code and adding tests require the agent to ingest user-provided project files and subsequently execute development tools like flutter test and dart fix --apply. This process creates a potential surface for indirect prompt injection, where instructions embedded in code comments or strings could influence the agent's behavior during analysis or command execution.
Ingestion points: SKILL.md workflows (review, add-tests) which involve reading existing Dart and configuration files.
Boundary markers: There are no explicit instructions or delimiters used to ensure the agent ignores natural language instructions that might be contained within the code it is analyzing.
Capability inventory: The skill utilizes subprocess calls to execute flutter analyze, flutter test, dart format, and dart fix --apply (providing both execution and file-write capabilities).
Sanitization: The skill does not implement validation or sanitization of the input code before invoking these development tools.
[EXTERNAL_DOWNLOADS]: The skill references external documentation and source code from established repositories, such as the official Flutter and Dart projects on GitHub. These references are standard for a technical development guide and target well-known, reputable services.
[COMMAND_EXECUTION]: The skill makes use of common CLI tools including flutter and dart. The execution of these commands is necessary for performing the skill's defined tasks, such as linting, testing, and formatting code, and is consistent with standard development practices.

flutter