The Agent Skills Directory

[SAFE]: No security threats or malicious patterns were identified. The skill's primary function is to provide architectural guidance and validation rules for developers.
[PROMPT_INJECTION]: The instructions focus strictly on architectural enforcement and right-sizing project tiers. There are no attempts to bypass safety filters or override system instructions.
[DATA_EXFILTRATION]: No hardcoded credentials, sensitive file path accesses, or unauthorized network operations were found. References to authentication (e.g., JWT, OAuth2) are provided as architectural examples only.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote code downloads or execution. It references standard tools like pytest and vitest for testing purposes within a development context.
[COMMAND_EXECUTION]: Documentation includes examples of CLI commands for testing and coverage analysis (e.g., pytest --cov, npm test -- --coverage), which are standard for the described use case.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to ingest and validate code (an external data source), it acts as a set of rules for the agent rather than an executable script. No vulnerability to indirect injection was identified in the static rules provided.

architecture-patterns