scripts: report a missing script program before scanning (#965)

Scripts are run through `sh -c`, so when the program a `call_format`
starts with is missing, the only feedback is whatever the shell prints
once the scan has already finished:

    Open 127.0.0.1:18080
    [~] Starting Script(s)
    [!] Error No such file or directory (os error 2)

which neither names the program nor arrives before a long scan has been
wasted.

Check the first word of every selected script format against PATH while
the scripts are initialised, and fail there with the program named. Name
resolution follows what the shell would do: PATH entries in order, plus
PATHEXT on Windows.

Formats that do not start with a bare program name are left alone, since
their first word is not something PATH can answer for:

- `FOO=bar cmd ...` (leading assignment)
- `/opt/custom/nmap ...` (explicit path)
- `{{script}} ...` (placeholder filled in at run time)

With nmap absent, on the same scan:

    before: scans, then "[!] Error No such file or directory (os error 2)"
    after:  "[!] Initiating scripts failed!
             The script `default` runs `nmap`, which is not installed or
             not in PATH. Install it, or skip scripts with `--scripts none`."

With nmap present the scan and the script phase run as before.

Implemented with std/target-specific helpers rather than a new
dependency: `which` pulls in a newer windows-sys and rewrites ~110 lines
of Cargo.lock for a 15-line check.

Refs #691

Co-authored-by: QianEric <[email protected]>

src/input.rs

@@ -25,8 +25,11 @@ pub enum ScanOrder {
 ///   - custom will read the ScriptConfig file and the available scripts in the predefined folders
 #[derive(Deserialize, Debug, ValueEnum, Clone, PartialEq, Eq, Copy)]
 pub enum ScriptsRequired {
+    #[serde(alias = "none")]
     None,
+    #[serde(alias = "default")]
     Default,
+    #[serde(alias = "custom")]
     Custom,
 }
 
@@ -526,6 +529,55 @@ mod tests {
         }
     }
 
+    fn assert_config_script_mode(value: &str, expected: ScriptsRequired) {
+        let config: Config = toml::from_str(&format!("scripts = \"{value}\""))
+            .expect("documented script mode must deserialize");
+        assert_eq!(config.scripts, Some(expected));
+    }
+
+    #[test]
+    fn config_scripts_lowercase_none() {
+        assert_config_script_mode("none", ScriptsRequired::None);
+    }
+
+    #[test]
+    fn config_scripts_lowercase_default() {
+        assert_config_script_mode("default", ScriptsRequired::Default);
+    }
+
+    #[test]
+    fn config_scripts_lowercase_custom() {
+        assert_config_script_mode("custom", ScriptsRequired::Custom);
+    }
+
+    #[test]
+    fn config_scripts_legacy_and_unknown_controls() {
+        assert_config_script_mode("None", ScriptsRequired::None);
+        assert_config_script_mode("Default", ScriptsRequired::Default);
+        assert_config_script_mode("Custom", ScriptsRequired::Custom);
+        for invalid in ["disabled", "unknown", ""] {
+            assert!(toml::from_str::<Config>(&format!("scripts = \"{invalid}\"")).is_err());
+        }
+    }
+
+    #[test]
+    fn config_read_accepts_documented_lowercase_script_modes() {
+        for (value, expected) in [
+            ("none", ScriptsRequired::None),
+            ("default", ScriptsRequired::Default),
+            ("custom", ScriptsRequired::Custom),
+        ] {
+            let fixture = std::env::temp_dir().join(format!(
+                "rustscan-config-scripts-{}-{value}.toml",
+                std::process::id()
+            ));
+            std::fs::write(&fixture, format!("scripts = \"{value}\"\n")).unwrap();
+            let config = Config::read(Some(fixture.clone()));
+            std::fs::remove_file(fixture).unwrap();
+            assert_eq!(config.scripts, Some(expected));
+        }
+    }
+
     #[test]
     fn verify_cli() {
         Opts::command().debug_assert();

src/main.rs

@@ -128,20 +128,7 @@ fn main() {
         map.entry(socket.ip()).or_default().push(socket.port());
     }
 
-    for ip in ips {
-        if ports_per_ip.contains_key(&ip) {
-            continue;
-        }
-
-        // If we got here it means the IP was not found within the HashMap, this
-        // means the scan couldn't find any open ports for it.
-
-        let x = format!("Looks like I didn't find any open ports for {:?}. This is usually caused by a high batch size.
-        \n*I used {} batch size, consider lowering it with {} or a comfortable number for your system.
-        \n Alternatively, increase the timeout if your ping is high. Rustscan -t 2000 for 2000 milliseconds (2s) timeout.\n",
-        ip,
-        batch_size,
-        "'rustscan -b <batch_size> -a <ip address>'");
+    if let Some(x) = no_open_ports_warning(&ips, &ports_per_ip, &closed_ports_per_ip, batch_size) {
         warning!(x, opts.greppable, opts.accessible);
     }
 
@@ -224,6 +211,35 @@ fn main() {
     info!("{}", benchmarks.summary());
 }
 
+/// Builds the hint printed when the scan found no open ports.
+///
+/// A host without open ports is normal when another host answered (a subnet
+/// sweep for one port): replies got through at this batch size and timeout,
+/// so batch size and timeout are unlikely to be the cause. The hint is printed
+/// once, and only when no host answered with an open or, under `--closed`, a
+/// closed port.
+fn no_open_ports_warning(
+    ips: &[IpAddr],
+    ports_per_ip: &HashMap<IpAddr, Vec<u16>>,
+    closed_ports_per_ip: &HashMap<IpAddr, Vec<u16>>,
+    batch_size: usize,
+) -> Option<String> {
+    if !ports_per_ip.is_empty() || !closed_ports_per_ip.is_empty() {
+        return None;
+    }
+
+    let target = match ips {
+        [ip] => format!("for {ip:?}"),
+        _ => format!("on any of the {} addresses", ips.len()),
+    };
+    Some(format!("Looks like I didn't find any open ports {}. This is usually caused by a high batch size.
+        \n*I used {} batch size, consider lowering it with {} or a comfortable number for your system.
+        \n Alternatively, increase the timeout if your ping is high. Rustscan -t 2000 for 2000 milliseconds (2s) timeout.\n",
+        target,
+        batch_size,
+        "'rustscan -b <batch_size> -a <ip address>'"))
+}
+
 /// Determines the actual batch size used by the scanner.
 ///
 /// Unix systems may reduce the requested batch size according to the process
@@ -373,7 +389,48 @@ mod tests {
     use super::effective_batch_size;
     #[cfg(unix)]
     use super::{adjust_ulimit_size, infer_batch_size};
-    use super::{print_opening, Opts};
+    use super::{no_open_ports_warning, print_opening, Opts};
+    use std::collections::HashMap;
+    use std::net::IpAddr;
+
+    fn hosts(n: u8) -> Vec<IpAddr> {
+        (1..=n).map(|i| IpAddr::from([192, 0, 2, i])).collect()
+    }
+
+    #[test]
+    fn no_open_ports_silent_when_another_host_answered() {
+        // Sweeping a subnet for one port: one host has it open, the rest do not.
+        let ips = hosts(254);
+        let ports_per_ip = HashMap::from([(ips[0], vec![22])]);
+
+        assert!(no_open_ports_warning(&ips, &ports_per_ip, &HashMap::new(), 4500).is_none());
+    }
+
+    #[test]
+    fn no_open_ports_silent_when_a_host_answered_closed() {
+        // With --closed, a refused connection also proves replies get through.
+        let ips = hosts(254);
+        let closed_ports_per_ip = HashMap::from([(ips[0], vec![443])]);
+
+        assert!(no_open_ports_warning(&ips, &HashMap::new(), &closed_ports_per_ip, 4500).is_none());
+    }
+
+    #[test]
+    fn no_open_ports_warns_once_when_nothing_found() {
+        let warning = no_open_ports_warning(&hosts(254), &HashMap::new(), &HashMap::new(), 4500);
+
+        let warning = warning.expect("one hint when nothing was found");
+        assert!(warning.contains("on any of the 254 addresses."));
+        assert!(warning.contains("4500 batch size"));
+    }
+
+    #[test]
+    fn no_open_ports_names_the_single_host() {
+        let warning = no_open_ports_warning(&hosts(1), &HashMap::new(), &HashMap::new(), 4500);
+
+        let warning = warning.expect("one hint for the single host");
+        assert!(warning.contains("for 192.0.2.1."));
+    }
 
     #[test]
     #[cfg(unix)]

src/scripts/mod.rs

@@ -143,9 +143,78 @@ pub fn init_scripts(scripts: &ScriptsRequired) -> Result<Vec<ScriptFile>> {
         }
     }
 
+    verify_script_programs(&scripts_to_run)?;
+
     Ok(scripts_to_run)
 }
 
+/// Whether `path/program` is something the shell could run.
+#[cfg(not(windows))]
+fn program_exists_in(dir: &std::path::Path, program: &str) -> bool {
+    dir.join(program).is_file()
+}
+
+/// Whether `path/program` is something `cmd.exe` could run, which appends
+/// entries from `PATHEXT` to a bare name.
+#[cfg(windows)]
+fn program_exists_in(dir: &std::path::Path, program: &str) -> bool {
+    if dir.join(program).is_file() {
+        return true;
+    }
+    let extensions = std::env::var("PATHEXT").unwrap_or_default();
+    extensions
+        .split(';')
+        .filter(|extension| !extension.is_empty())
+        .any(|extension| dir.join(format!("{program}{extension}")).is_file())
+}
+
+fn program_is_available(program: &str) -> bool {
+    match std::env::var_os("PATH") {
+        Some(path) => std::env::split_paths(&path).any(|dir| program_exists_in(&dir, program)),
+        None => false,
+    }
+}
+
+/// Check that the program each selected script starts with is available.
+///
+/// Scripts run through `sh -c`, so a missing binary surfaces only as a bare
+/// "Exit code = 127" once the scan has already finished. Report it up front
+/// instead, before a long scan has been wasted.
+fn verify_script_programs(scripts_to_run: &[ScriptFile]) -> Result<()> {
+    for script in scripts_to_run {
+        let call_format = match &script.call_format {
+            Some(call_format) => call_format,
+            None => continue,
+        };
+        let program = match call_format.split_whitespace().next() {
+            Some(program) => program,
+            None => continue,
+        };
+        // A leading assignment (`FOO=bar nmap ...`) or an absolute path is not
+        // a bare program name, and `{{...}}` placeholders are only filled in
+        // when the script actually runs, so leave those formats alone.
+        if program.contains('=')
+            || program.contains('/')
+            || program.contains('$')
+            || program.contains("{{")
+        {
+            continue;
+        }
+        if !program_is_available(program) {
+            return Err(anyhow!(
+                "The script `{}` runs `{}`, which is not installed or not in PATH. \
+                 Install it, or skip scripts with `--scripts none`.",
+                script
+                    .path
+                    .as_ref()
+                    .map_or_else(|| "default".to_string(), |path| path.display().to_string()),
+                program
+            ));
+        }
+    }
+    Ok(())
+}
+
 pub fn parse_scripts(scripts: Vec<PathBuf>) -> Vec<ScriptFile> {
     let mut parsed_scripts: Vec<ScriptFile> = Vec::with_capacity(scripts.len());
     for script in scripts {
@@ -348,8 +417,7 @@ impl ScriptFile {
         if let Ok(file) = File::open(script) {
             for mut line in io::BufReader::new(file).lines().skip(1).flatten() {
                 if line.starts_with('#') {
-                    line.retain(|c| c != '#');
-                    line = line.trim().to_string();
+                    line = line[1..].trim().to_string();
                     line.push('\n');
                     lines_buf.push_str(&line);
                 } else {
@@ -403,6 +471,21 @@ impl ScriptConfig {
 mod tests {
     use super::*;
 
+    #[test]
+    fn script_headers_preserve_literal_hash_characters() {
+        let fixture =
+            std::env::temp_dir().join(format!("rustscan-literal-hash-{}.txt", std::process::id()));
+        fs::write(&fixture, "#!/usr/bin/env python3\n#tags = [\"C#\"]\n#call_format = \"fixture {{ip}} {{port}} https://example.invalid/#section\"\n\n").unwrap();
+        let parsed = ScriptFile::new(fixture.clone());
+        fs::remove_file(fixture).unwrap();
+        let parsed = parsed.expect("valid TOML metadata");
+        assert_eq!(parsed.tags, Some(vec!["C#".to_owned()]));
+        assert_eq!(
+            parsed.call_format.as_deref(),
+            Some("fixture {{ip}} {{port}} https://example.invalid/#section")
+        );
+    }
+
     #[test]
     fn find_and_parse_scripts() {
         let scripts = find_scripts("fixtures/.rustscan_scripts".into()).unwrap();
@@ -495,4 +578,40 @@ mod tests {
 
         assert_eq!(script_dir_base, dirs::home_dir().unwrap());
     }
+
+    fn script_with_call_format(call_format: &str) -> ScriptFile {
+        ScriptFile {
+            path: Some(PathBuf::from("/tmp/script.txt")),
+            tags: None,
+            developer: None,
+            port: None,
+            ports_separator: None,
+            call_format: Some(call_format.to_string()),
+        }
+    }
+
+    #[test]
+    fn missing_script_program_is_reported() {
+        let scripts = vec![script_with_call_format("definitely-not-a-real-binary {{ip}}")];
+        let err = verify_script_programs(&scripts).unwrap_err();
+        assert!(err.to_string().contains("definitely-not-a-real-binary"));
+    }
+
+    #[test]
+    fn available_script_program_is_accepted() {
+        // `sh` is what the scripts are actually run through, so it is present
+        // on every platform that can execute them.
+        let scripts = vec![script_with_call_format("sh -c true {{ip}}")];
+        assert!(verify_script_programs(&scripts).is_ok());
+    }
+
+    #[test]
+    fn placeholder_and_assignment_prefixes_are_skipped() {
+        let scripts = vec![
+            script_with_call_format("{{script}} {{ip}} {{port}}"),
+            script_with_call_format("FOO=bar definitely-not-a-real-binary"),
+            script_with_call_format("/opt/custom/nmap {{ip}}"),
+        ];
+        assert!(verify_script_programs(&scripts).is_ok());
+    }
 }