From 4a45c14742e6868f687cead2ddf736c3f7c49acd Mon Sep 17 00:00:00 2001
From: morluto <76467478+morluto@users.noreply.github.com>
Date: Fri, 9 Oct 2026 04:40:47 +0800
Subject: [PATCH] fix(firmware): reject malformed UTF-8 producer reports

---
 docs/firmware-analysis.md                     |  5 ++-
 src/firmware/FirmwareFiles.ts                 |  6 ++-
 .../firmware/firmwareReportFiles.test.ts      | 43 +++++++++++++++++++
 3 files changed, 51 insertions(+), 3 deletions(-)
 create mode 100644 tests/boundary/firmware/firmwareReportFiles.test.ts

diff --git a/docs/firmware-analysis.md b/docs/firmware-analysis.md
index 1796ef43a..12886bd0d 100644
--- a/docs/firmware-analysis.md
+++ b/docs/firmware-analysis.md
@@ -129,8 +129,9 @@ tree semantics, vulnerability scanning, emulation or hardware runtime capture.
   Unblob one worker. No automatic parallel extraction engines.
 - **120-second** deadline; inherited **1 GiB per-process address-space** limit,
   120 CPU seconds and zero core-dump allowance through `prlimit`.
-- JSON reports: at most **8 MiB**; oversized reports fail without a truncated
-  success. Diagnostic output is bounded with exact captured byte counts.
+- JSON reports: at most **8 MiB** and valid UTF-8; malformed encoding and
+  oversized reports fail without repairing or truncating producer data.
+  Diagnostic output is bounded with exact captured byte counts.
 - Default staging budget: **256 MiB** and **10,000 entries**, configurable using
   `max_output_bytes` / `max_output_files` (CLI `--max-output-bytes` /
   `--max-output-files`). Depth defaults to 3, allowed range 1–10.
diff --git a/src/firmware/FirmwareFiles.ts b/src/firmware/FirmwareFiles.ts
index ad63b49de..a118984b8 100644
--- a/src/firmware/FirmwareFiles.ts
+++ b/src/firmware/FirmwareFiles.ts
@@ -153,7 +153,11 @@ export const readFirmwareReport = async (
         `Report exceeded ${FIRMWARE_LIMITS.reportBytes} bytes`,
       );
     try {
-      const value: unknown = JSON.parse(bytes.toString("utf8"));
+      const value: unknown = JSON.parse(
+        new TextDecoder("utf-8", { fatal: true, ignoreBOM: true }).decode(
+          bytes,
+        ),
+      );
       return value;
     } catch (cause: unknown) {
       throw new AnalysisOutputError(
diff --git a/tests/boundary/firmware/firmwareReportFiles.test.ts b/tests/boundary/firmware/firmwareReportFiles.test.ts
new file mode 100644
index 000000000..f3a181624
--- /dev/null
+++ b/tests/boundary/firmware/firmwareReportFiles.test.ts
@@ -0,0 +1,43 @@
+import { writeFile } from "node:fs/promises";
+import { join } from "node:path";
+import { expect, it } from "vitest";
+
+import { readFirmwareReport } from "../../../src/firmware/FirmwareFiles.js";
+import { createTestTempDirectory } from "../../fixtures/temporaryDirectory.js";
+
+it.each([
+  ["invalid leading byte", [0xff]],
+  ["incomplete sequence", [0xe2, 0x82]],
+  ["overlong sequence", [0xc0, 0xaf]],
+  ["encoded surrogate", [0xed, 0xa0, 0x80]],
+])(
+  "rejects complete JSON containing %s without repairing producer bytes",
+  async (_name, bytes) => {
+    const root = await createTestTempDirectory("rea-firmware-report-");
+    const path = join(root, "report.json");
+    await writeFile(
+      path,
+      Buffer.concat([
+        Buffer.from('{"description":"'),
+        Buffer.from(bytes),
+        Buffer.from('"}'),
+      ]),
+    );
+    await expect(
+      readFirmwareReport(path, "inspect_firmware_regions"),
+    ).rejects.toMatchObject({
+      _tag: "AnalysisOutputError",
+      reason: "Tool report is not valid complete JSON",
+    });
+  },
+);
+
+it("preserves valid Unicode and a literal replacement character in producer JSON", async () => {
+  const root = await createTestTempDirectory("rea-firmware-report-");
+  const path = join(root, "report.json");
+  const report = { description: "固件 🧩 \ufffd", path: "/输入/firmware.bin" };
+  await writeFile(path, JSON.stringify(report));
+  expect(await readFirmwareReport(path, "inspect_firmware_regions")).toEqual(
+    report,
+  );
+});