from logs-windows.powershell_operational* metadata _id, _version, _index
| where event.code == "4104"

// replace repeated spaces used for formatting after a new line with a single space to reduce FPs
| eval Esql.script_block_tmp = replace(powershell.file.script_block_text, """\n\s+""", "\n ")

// Look for scripts with more than 1000 chars
| eval Esql.script_block_length = length(Esql.script_block_tmp)
| where Esql.script_block_length > 1000

// replace the patterns we are looking for with the 🔥 emoji to enable counting them
// The emoji is used because it's unlikely to appear in scripts and has a consistent character length of 1
| eval Esql.script_block_tmp = replace(
    Esql.script_block_tmp,
    """[\s\$\{\}\+\@\=\(\)\^\\\"~\[\]\?\.]""",
    "🔥"
)

// count how many patterns were detected by calculating the number of 🔥 characters inserted
| eval Esql.script_block_count = Esql.script_block_length - length(replace(Esql.script_block_tmp, "🔥", ""))

// Calculate the ratio of special characters to total length
| eval Esql.script_block_ratio = Esql.script_block_count::double / Esql.script_block_length::double

// keep the fields relevant to the query, although this is not needed as the alert is populated using _id
| keep
    Esql.script_block_count,
    Esql.script_block_length,
    Esql.script_block_ratio,
    Esql.script_block_tmp,
    powershell.file.script_block_text,
    powershell.file.script_block_id,
    file.path,
    powershell.sequence,
    powershell.total,
    _id,
    _index,
    host.name,
    agent.id,
    user.id

// Filter for scripts with high whitespace and special character ratio
| where Esql.script_block_ratio > 0.75