The Agent Skills Directory

[SAFE]: The skill follows security best practices by limiting its execution environment to necessary tools and specific test-running commands.- [COMMAND_EXECUTION]: Shell access is restricted through the allowed-tools configuration to specific test runners (go test, pytest, bun test, npm test), preventing arbitrary command execution while enabling its core functionality.- [DATA_EXFILTRATION]: No network activity or access to sensitive configuration files (e.g., .ssh, .aws, .env) was found. All operations are local to the code repository.- [PROMPT_INJECTION]: The instructions do not contain attempts to override agent constraints or bypass safety filters.

improving-tests