The Agent Skills Directory

[SAFE]: The skill provides structured guidelines for reviewing and refactoring Flutter code based on official documentation from trusted sources (Google/Flutter). No malicious patterns such as obfuscation, credential theft, or unauthorized remote code execution were detected.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of Flutter code (SKILL.md, Required Workflow). It instructs the agent to perform actions such as running flutter test on the provided project. While this represents a surface for indirect prompt injection or execution of malicious code within a testing framework, this capability is inherent to the skill's primary purpose of code verification. The skill currently lacks explicit boundary markers or instructions to sanitize inputs.

flutter-modern-reviewer