Detect Trojan Source in source code

The same thing in your own code

Each code block has been compiled and verified in CI. Provided under the MIT license to illustrate disarm. These operate on the single commenting-out line from the Trojan Source paper, which carries four of the six controls in the sample file the tool above loads — hence controls == 4 beside a table listing six. disarm on GitHub →

# Detect Trojan Source, and the direction conflict that stripping cannot fix.
#   pip install disarm
from disarm import strip_bidi, has_bidi_conflict

# The commenting-out line from the Trojan Source paper: an override and two
# isolates, so the `if` appears to sit inside the comment.
TROJAN = "    /*‮ } ⁩if (isAdmin)⁦ ⁦ begin admins only */"
# No control character at all — the final letter is a real Hebrew vav.
CONFLICT = "varonis.com.ו"

clean = strip_bidi(TROJAN)
controls = len(TROJAN) - len(clean)

# The two checks catch different attacks, which is why both are needed.
assert controls == 4, controls
assert not has_bidi_conflict(TROJAN), "overrides are not a direction conflict"
assert has_bidi_conflict(CONFLICT), "real RTL letters are"
assert strip_bidi(CONFLICT) == CONFLICT, "and there is nothing to strip"

print(f"ok: {controls} bidi controls stripped; a conflict detected where there are none")

// Detect Trojan Source, and the direction conflict that stripping cannot fix.
//   cargo add disarm
use disarm::api::{has_bidi_conflict, strip_bidi};

fn main() {
    // The commenting-out line from the Trojan Source paper: an override and two
    // isolates, so the `if` appears to sit inside the comment.
    let trojan = "    /*\u{202e} } \u{2069}if (isAdmin)\u{2066} \u{2066} begin admins only */";
    // No control character at all — the final letter is a real Hebrew vav.
    let conflict = "varonis.com.\u{05d5}";

    let clean = strip_bidi(trojan);
    let controls = trojan.chars().count() - clean.chars().count();

    // The two checks catch different attacks, which is why both are needed.
    assert_eq!(controls, 4);
    assert!(!has_bidi_conflict(trojan), "overrides are not a direction conflict");
    assert!(has_bidi_conflict(conflict), "real RTL letters are");
    assert_eq!(strip_bidi(conflict), conflict, "and there is nothing to strip");

    println!("ok: {controls} bidi controls stripped; a conflict detected where there are none");
}

// Detect Trojan Source, and the direction conflict that stripping cannot fix.
//   npm i disarm
const assert = require("node:assert/strict");
const { stripBidi, hasBidiConflict } = require("disarm");

// The commenting-out line from the Trojan Source paper: an override and two
// isolates, so the `if` appears to sit inside the comment.
const TROJAN = "    /*‮ } ⁩if (isAdmin)⁦ ⁦ begin admins only */";
// No control character at all — the final letter is a real Hebrew vav.
const CONFLICT = "varonis.com.ו";

const clean = stripBidi(TROJAN);
const controls = [...TROJAN].length - [...clean].length;

// The two checks catch different attacks, which is why both are needed.
assert.equal(controls, 4);
assert.ok(!hasBidiConflict(TROJAN), "overrides are not a direction conflict");
assert.ok(hasBidiConflict(CONFLICT), "real RTL letters are");
assert.equal(stripBidi(CONFLICT), CONFLICT, "and there is nothing to strip");

console.log(`ok: ${controls} bidi controls stripped; a conflict detected where there are none`);

# Detect Trojan Source, and the direction conflict that stripping cannot fix.
#   gem install disarm
require "disarm"

# The commenting-out line from the Trojan Source paper: an override and two
# isolates, so the `if` appears to sit inside the comment.
TROJAN = "    /*‮ } ⁩if (isAdmin)⁦ ⁦ begin admins only */"
# No control character at all — the final letter is a real Hebrew vav.
CONFLICT = "varonis.com.ו"

clean = Disarm.strip_bidi(TROJAN)
controls = TROJAN.length - clean.length

# The two checks catch different attacks, which is why both are needed.
raise "expected 4, got #{controls}" unless controls == 4
raise "overrides are not a direction conflict" if Disarm.bidi_conflict?(TROJAN)
raise "real RTL letters are" unless Disarm.bidi_conflict?(CONFLICT)
raise "and there is nothing to strip" unless Disarm.strip_bidi(CONFLICT) == CONFLICT

puts "ok: #{controls} bidi controls stripped; a conflict detected where there are none"

// Detect Trojan Source, and the direction conflict that stripping cannot fix.
//   implementation("dev.disarm:disarm:0.14.1")
import dev.disarm.Disarm;

public class DetectBidi {
    public static void main(String[] args) {
        // The commenting-out line from the Trojan Source paper: an override and
        // two isolates, so the `if` appears to sit inside the comment. Written
        // with literal characters rather than backslash-u escapes, because javac
        // resolves those before tokenizing — even inside a comment. Writing that
        // escape sequence here, in this very comment, is itself a compile error,
        // which is the hazard stated more plainly than any wording could.
        String trojan = "    /*‮ } ⁩if (isAdmin)⁦ ⁦ begin admins only */";
        // No control character at all — the final letter is a real Hebrew vav.
        String conflict = "varonis.com.ו";

        String clean = Disarm.stripBidi(trojan);
        long controls = trojan.codePointCount(0, trojan.length())
                      - clean.codePointCount(0, clean.length());

        // The two checks catch different attacks, which is why both are needed.
        if (controls != 4) throw new AssertionError("expected 4, got " + controls);
        if (Disarm.hasBidiConflict(trojan)) throw new AssertionError("overrides are not a direction conflict");
        if (!Disarm.hasBidiConflict(conflict)) throw new AssertionError("real RTL letters are");
        if (!Disarm.stripBidi(conflict).equals(conflict)) throw new AssertionError("and there is nothing to strip");

        System.out.printf("ok: %d bidi controls stripped; a conflict detected where there are none%n", controls);
    }
}

// Detect Trojan Source, and the direction conflict that stripping cannot fix.
//   implementation("dev.disarm:disarm-kotlin:0.14.1")
import dev.disarm.kotlin.*

fun main() {
    // The commenting-out line from the Trojan Source paper: an override and two
    // isolates, so the `if` appears to sit inside the comment.
    val trojan = "    /*‮ } ⁩if (isAdmin)⁦ ⁦ begin admins only */"
    // No control character at all — the final letter is a real Hebrew vav.
    val conflict = "varonis.com.ו"

    val controls = trojan.codePointCount(0, trojan.length) -
        trojan.stripBidi().let { it.codePointCount(0, it.length) }

    // The two checks catch different attacks, which is why both are needed.
    check(controls == 4) { "expected 4, got $controls" }
    check(!trojan.hasBidiConflict()) { "overrides are not a direction conflict" }
    check(conflict.hasBidiConflict()) { "real RTL letters are" }
    check(conflict.stripBidi() == conflict) { "and there is nothing to strip" }

    println("ok: $controls bidi controls stripped; a conflict detected where there are none")
}

/* Detect Trojan Source, and the direction conflict that stripping cannot fix.
 *
 * The C ABI is not published to any registry, so this links against a cdylib
 * built from bindings/cabi in the disarm repository.
 */
#include <stdio.h>
#include <string.h>
#include "disarm.h"

/* Count UTF-8 codepoints, so the control characters are counted as one each. */
static size_t cp_len(const char *s) {
    size_t n = 0;
    for (; *s; s++) if ((*s & 0xC0) != 0x80) n++;
    return n;
}

int main(void) {
    /* The commenting-out line from the Trojan Source paper: an override and two
     * isolates, so the `if` appears to sit inside the comment. */
    const char *trojan = "    /*\U0000202E } \U00002069if (isAdmin)\U00002066 \U00002066 begin admins only */";
    /* No control character at all — the final letter is a real Hebrew vav. */
    const char *conflict = "varonis.com.\U000005D5";

    char *clean = disarm_strip_bidi(trojan);
    size_t controls = cp_len(trojan) - cp_len(clean);

    /* The two checks catch different attacks, which is why both are needed. */
    if (controls != 4) { fprintf(stderr, "expected 4, got %zu\n", controls); return 1; }
    if (disarm_has_bidi_conflict(trojan)) { fprintf(stderr, "overrides are not a conflict\n"); return 1; }
    if (!disarm_has_bidi_conflict(conflict)) { fprintf(stderr, "real RTL letters are\n"); return 1; }

    char *conflict_clean = disarm_strip_bidi(conflict);
    if (strcmp(conflict_clean, conflict) != 0) { fprintf(stderr, "nothing should be stripped\n"); return 1; }
    disarm_string_free(conflict_clean);

    printf("ok: %zu bidi controls stripped; a conflict detected where there are none\n", controls);
    disarm_string_free(clean);
    return 0;
}