feat: add sanitizer to redact secrets (#11600)

Adding a sanitizer crate that can redact API keys and other secret with
known pattern from a String

codex-rs/Cargo.lock

@@ -2485,6 +2485,13 @@ dependencies = [
  "pretty_assertions",
 ]
 
+[[package]]
+name = "codex-utils-sanitizer"
+version = "0.0.0"
+dependencies = [
+ "regex",
+]
+
 [[package]]
 name = "codex-utils-string"
 version = "0.0.0"

codex-rs/Cargo.toml

@@ -53,6 +53,7 @@ members = [
     "utils/cli",
     "utils/elapsed",
     "utils/sandbox-summary",
+    "utils/sanitizer",
     "utils/approval-presets",
     "utils/oss",
     "utils/fuzzy-match",
@@ -129,6 +130,7 @@ codex-utils-pty = { path = "utils/pty" }
 codex-utils-readiness = { path = "utils/readiness" }
 codex-utils-rustls-provider = { path = "utils/rustls-provider" }
 codex-utils-sandbox-summary = { path = "utils/sandbox-summary" }
+codex-utils-sanitizer = { path = "utils/sanitizer" }
 codex-utils-string = { path = "utils/string" }
 codex-windows-sandbox = { path = "windows-sandbox-rs" }
 core_test_support = { path = "core/tests/common" }
@@ -338,6 +340,7 @@ ignored = [
     "icu_provider",
     "openssl-sys",
     "codex-utils-readiness",
+    "codex-utils-sanitizer",
     "codex-secrets",
 ]
 

codex-rs/utils/sanitizer/Cargo.toml

@@ -0,0 +1,11 @@
+[package]
+name = "codex-utils-sanitizer"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[dependencies]
+regex = "1.12.3"
+
+[lints]
+workspace = true

codex-rs/utils/sanitizer/src/lib.rs

@@ -0,0 +1,41 @@
+use regex::Regex;
+use std::sync::LazyLock;
+
+static OPENAI_KEY_REGEX: LazyLock<Regex> = LazyLock::new(|| compile_regex(r"sk-[A-Za-z0-9]{20,}"));
+static AWS_ACCESS_KEY_ID_REGEX: LazyLock<Regex> =
+    LazyLock::new(|| compile_regex(r"\bAKIA[0-9A-Z]{16}\b"));
+static BEARER_TOKEN_REGEX: LazyLock<Regex> =
+    LazyLock::new(|| compile_regex(r"(?i)\bBearer\s+[A-Za-z0-9._\-]{16,}\b"));
+static SECRET_ASSIGNMENT_REGEX: LazyLock<Regex> = LazyLock::new(|| {
+    compile_regex(r#"(?i)\b(api[_-]?key|token|secret|password)\b(\s*[:=]\s*)(["']?)[^\s"']{8,}"#)
+});
+
+/// Remove secret and keys from a String. This is done on best effort basis following some
+/// well-known REGEX.
+pub fn redact_secrets(input: String) -> String {
+    let redacted = OPENAI_KEY_REGEX.replace_all(&input, "[REDACTED_SECRET]");
+    let redacted = AWS_ACCESS_KEY_ID_REGEX.replace_all(&redacted, "[REDACTED_SECRET]");
+    let redacted = BEARER_TOKEN_REGEX.replace_all(&redacted, "Bearer [REDACTED_SECRET]");
+    let redacted = SECRET_ASSIGNMENT_REGEX.replace_all(&redacted, "$1$2$3[REDACTED_SECRET]");
+
+    redacted.to_string()
+}
+
+fn compile_regex(pattern: &str) -> Regex {
+    match Regex::new(pattern) {
+        Ok(regex) => regex,
+        // Panic is ok thanks to `load_regex` test.
+        Err(err) => panic!("invalid regex pattern `{pattern}`: {err}"),
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn load_regex() {
+        // The goal of this test is just to compile all the regex to prevent the panic
+        let _ = redact_secrets("secret".to_string());
+    }
+}