From 889ed789328a2de59fe8cda220fa2e98e756f350 Mon Sep 17 00:00:00 2001
From: Garry Tan <garrytan@gmail.com>
Date: Fri, 29 May 2026 07:07:28 -0700
Subject: [PATCH] feat(redact): opt-in pre-push hook (accident catcher) + safe
 installer

bin/gstack-redact-prepush scans the diff being pushed for HIGH credentials and
blocks on a hit, for public AND private repos (a pushed secret is compromised
regardless of visibility). Correct git pre-push semantics: scans remote..local
(what's being pushed), handles new-branch zero-SHA via merge-base or empty-tree
fallback, force-push, and branch-delete skip. MEDIUM warns non-blocking; LOW/WARN
silent. GSTACK_REDACT_PREPUSH=skip escape valve logs to prepush-skip.jsonl.

bin/gstack-redact gains install-prepush-hook / uninstall-prepush-hook
subcommands that chain any pre-existing hook (renamed to pre-push.local,
stdin forwarded to both, exit code propagated).

Guardrail not enforcement: --no-verify and the env skip both bypass; it scans
only the pushed delta, not history/binary/LFS. 9 tests in a throwaway git repo.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 bin/gstack-redact                |  72 +++++++++++++++
 bin/gstack-redact-prepush        | 146 +++++++++++++++++++++++++++++
 test/redact-prepush-hook.test.ts | 153 +++++++++++++++++++++++++++++++
 3 files changed, 371 insertions(+)
 create mode 100755 bin/gstack-redact-prepush
 create mode 100644 test/redact-prepush-hook.test.ts

diff --git a/bin/gstack-redact b/bin/gstack-redact
index 8f61e6580..ccb6e48c5 100755
--- a/bin/gstack-redact
+++ b/bin/gstack-redact
@@ -27,6 +27,8 @@
  * user can always bypass it (direct gh/git). It catches accidents.
  */
 import * as fs from "fs";
+import * as path from "path";
+import { spawnSync } from "child_process";
 import {
   scan,
   applyRedactions,
@@ -38,6 +40,71 @@ import {
 
 const MAX_STDIN_BYTES = 16 * 1024 * 1024; // hard ceiling before the engine cap
 
+// ── pre-push hook install/uninstall (chains any existing hook) ────────────────
+
+const MANAGED_MARKER = "# gstack-redact pre-push (managed)";
+
+function hooksPath(): string {
+  const r = spawnSync("git", ["rev-parse", "--git-path", "hooks"], { encoding: "utf8" });
+  if (r.status !== 0) {
+    process.stderr.write("gstack-redact: not in a git repo\n");
+    process.exit(1);
+  }
+  return r.stdout.trim();
+}
+
+function installPrepushHook(): void {
+  const dir = hooksPath();
+  fs.mkdirSync(dir, { recursive: true });
+  const hookPath = path.join(dir, "pre-push");
+  const prepushBin = path.join(import.meta.dir, "gstack-redact-prepush");
+
+  // If a non-managed hook exists, preserve it as pre-push.local and chain it.
+  if (fs.existsSync(hookPath)) {
+    const existing = fs.readFileSync(hookPath, "utf8");
+    if (existing.includes(MANAGED_MARKER)) {
+      process.stdout.write("gstack-redact: pre-push hook already installed.\n");
+      return;
+    }
+    const localPath = path.join(dir, "pre-push.local");
+    fs.renameSync(hookPath, localPath);
+    fs.chmodSync(localPath, 0o755);
+    process.stdout.write("gstack-redact: preserved existing hook as pre-push.local (chained).\n");
+  }
+
+  // stdin is single-consume: capture it once, feed both the chained hook and ours.
+  const wrapper = `#!/usr/bin/env bash
+${MANAGED_MARKER}
+set -euo pipefail
+_input="$(cat)"
+_local="$(git rev-parse --git-path hooks/pre-push.local)"
+if [ -x "$_local" ]; then
+  printf '%s' "$_input" | "$_local" "$@" || exit $?
+fi
+printf '%s' "$_input" | bun "${prepushBin}" "$@"
+`;
+  fs.writeFileSync(hookPath, wrapper, { mode: 0o755 });
+  fs.chmodSync(hookPath, 0o755);
+  process.stdout.write(`gstack-redact: installed pre-push hook at ${hookPath}\n`);
+}
+
+function uninstallPrepushHook(): void {
+  const dir = hooksPath();
+  const hookPath = path.join(dir, "pre-push");
+  const localPath = path.join(dir, "pre-push.local");
+  if (!fs.existsSync(hookPath) || !fs.readFileSync(hookPath, "utf8").includes(MANAGED_MARKER)) {
+    process.stdout.write("gstack-redact: no managed pre-push hook to remove.\n");
+    return;
+  }
+  if (fs.existsSync(localPath)) {
+    fs.renameSync(localPath, hookPath); // restore the chained original
+    process.stdout.write("gstack-redact: removed managed hook, restored pre-push.local.\n");
+  } else {
+    fs.unlinkSync(hookPath);
+    process.stdout.write("gstack-redact: removed managed pre-push hook.\n");
+  }
+}
+
 function arg(name: string): string | undefined {
   const i = process.argv.indexOf(name);
   return i >= 0 ? process.argv[i + 1] : undefined;
@@ -115,6 +182,11 @@ function humanTable(findings: Finding[]): string {
 }
 
 function main() {
+  // Subcommands (positional, not flags).
+  const sub = process.argv[2];
+  if (sub === "install-prepush-hook") return installPrepushHook();
+  if (sub === "uninstall-prepush-hook") return uninstallPrepushHook();
+
   const opts = buildOpts();
   const input = readInput();
 
diff --git a/bin/gstack-redact-prepush b/bin/gstack-redact-prepush
new file mode 100755
index 000000000..25fc8c1d4
--- /dev/null
+++ b/bin/gstack-redact-prepush
@@ -0,0 +1,146 @@
+#!/usr/bin/env bun
+/**
+ * gstack-redact-prepush — git pre-push hook that scans the diff being pushed for
+ * HIGH-severity credentials and blocks the push on a hit.
+ *
+ * THIS IS A GUARDRAIL, NOT ENFORCEMENT. `git push --no-verify` bypasses it, as
+ * does `GSTACK_REDACT_PREPUSH=skip`. It catches accidental credential pushes,
+ * the most common real-world leak. It does NOT scan history, binary/LFS/submodule
+ * files, or non-added lines. History scanning is /cso's job.
+ *
+ * Git pre-push interface: refs are read from STDIN, one per line:
+ *   <local ref> <local sha> <remote ref> <remote sha>
+ * We scan the ADDED lines of <remote sha>..<local sha> per ref (what's being
+ * pushed). Special cases:
+ *   - remote sha all-zeroes  → new branch: diff against merge-base with the
+ *     remote's default branch (fallback: scan all commits unique to local ref).
+ *   - local sha all-zeroes   → branch delete: nothing to scan, skip.
+ *   - force-push             → remote..local still gives the net new content.
+ *
+ * Behavior:
+ *   - HIGH finding in added lines → print + exit 1 (block), for public AND private.
+ *   - MEDIUM → warn (non-blocking). LOW/WARN → silent.
+ *   - GSTACK_REDACT_PREPUSH=skip → log + exit 0 (escape valve).
+ *
+ * Installed/uninstalled via `gstack-redact install-prepush-hook` (see the
+ * gstack-redact CLI), which chains any pre-existing hook.
+ */
+import { spawnSync } from "child_process";
+import * as fs from "fs";
+import * as os from "os";
+import * as path from "path";
+import { scan, type Finding } from "../lib/redact-engine";
+
+const ZERO = /^0+$/;
+// The canonical empty-tree object; diffing against it yields all content as added.
+const EMPTY_TREE = "4b825dc642cb6eb9a060e54bf8d69288fbee4904";
+
+function git(args: string[]): string {
+  const r = spawnSync("git", args, { encoding: "utf8", maxBuffer: 64 * 1024 * 1024 });
+  return r.status === 0 ? (r.stdout ?? "") : "";
+}
+
+function defaultRemoteBranch(): string {
+  // origin/HEAD → origin/main, fall back to main/master.
+  const sym = git(["symbolic-ref", "refs/remotes/origin/HEAD"]).trim();
+  if (sym) return sym.replace("refs/remotes/", "");
+  for (const b of ["origin/main", "origin/master"]) {
+    if (git(["rev-parse", "--verify", b]).trim()) return b;
+  }
+  return "origin/main";
+}
+
+/** Return the added-line text for a ref update being pushed. */
+function addedLinesFor(localSha: string, remoteSha: string): string {
+  let range: string;
+  if (ZERO.test(remoteSha)) {
+    // New branch: prefer what's unique to localSha vs the remote default branch.
+    // With no merge-base (e.g. no remote yet), diff against the empty tree so ALL
+    // branch content is scanned as added — fail-safe (scans more, never less).
+    const base = git(["merge-base", localSha, defaultRemoteBranch()]).trim();
+    range = base ? `${base}..${localSha}` : `${EMPTY_TREE}..${localSha}`;
+  } else {
+    // Existing branch (incl. force-push): net new content remote..local.
+    range = `${remoteSha}..${localSha}`;
+  }
+  // -U0: only changed lines; we keep lines starting with '+' (added), drop the
+  // +++ file header. Unified diff added lines start with a single '+'.
+  const diff = git(["diff", "--unified=0", "--no-color", range]);
+  const added: string[] = [];
+  for (const line of diff.split("\n")) {
+    if (line.startsWith("+") && !line.startsWith("+++")) {
+      added.push(line.slice(1));
+    }
+  }
+  return added.join("\n");
+}
+
+function logSkip(reason: string): void {
+  try {
+    const home = process.env.GSTACK_HOME || path.join(os.homedir(), ".gstack");
+    const dir = path.join(home, "security");
+    fs.mkdirSync(dir, { recursive: true });
+    fs.appendFileSync(
+      path.join(dir, "prepush-skip.jsonl"),
+      JSON.stringify({ ts: new Date().toISOString(), reason }) + "\n",
+    );
+  } catch {
+    // best-effort; never block a push because logging failed
+  }
+}
+
+function main() {
+  if ((process.env.GSTACK_REDACT_PREPUSH || "").toLowerCase() === "skip") {
+    logSkip(process.env.GSTACK_REDACT_PREPUSH_REASON || "env-skip");
+    process.stderr.write("gstack-redact-prepush: skipped via GSTACK_REDACT_PREPUSH=skip\n");
+    process.exit(0);
+  }
+
+  const stdin = fs.readFileSync(0, "utf8");
+  const refs = stdin
+    .split("\n")
+    .map((l) => l.trim())
+    .filter(Boolean)
+    .map((l) => l.split(/\s+/));
+
+  const allHigh: Finding[] = [];
+  let mediumCount = 0;
+
+  for (const [, localSha, , remoteSha] of refs) {
+    if (!localSha || ZERO.test(localSha)) continue; // branch delete → nothing pushed
+    const added = addedLinesFor(localSha, remoteSha || "0");
+    if (!added.trim()) continue;
+    // Visibility doesn't change HIGH behavior; pass private so nothing is treated
+    // as public-strict (HIGH blocks regardless either way).
+    const result = scan(added, { repoVisibility: "private" });
+    for (const f of result.findings) {
+      if (f.severity === "HIGH") allHigh.push(f);
+      else if (f.severity === "MEDIUM") mediumCount++;
+    }
+  }
+
+  if (mediumCount > 0) {
+    process.stderr.write(
+      `gstack-redact-prepush: ${mediumCount} MEDIUM finding(s) in pushed diff (PII/internal). ` +
+        "Not blocking. Review before this becomes public.\n",
+    );
+  }
+
+  if (allHigh.length > 0) {
+    process.stderr.write(
+      "\n⛔ gstack-redact-prepush BLOCKED the push — credential(s) in the pushed diff:\n\n",
+    );
+    for (const f of allHigh) {
+      process.stderr.write(`  HIGH  ${f.id}  ${f.preview}\n`);
+    }
+    process.stderr.write(
+      "\nRotate the credential (a pushed secret is compromised) and remove it from the diff.\n" +
+        "This is a guardrail: `git push --no-verify` or `GSTACK_REDACT_PREPUSH=skip git push` bypass it.\n",
+    );
+    process.exit(1);
+  }
+
+  process.exit(0);
+}
+
+main();
diff --git a/test/redact-prepush-hook.test.ts b/test/redact-prepush-hook.test.ts
new file mode 100644
index 000000000..8447cf6d5
--- /dev/null
+++ b/test/redact-prepush-hook.test.ts
@@ -0,0 +1,153 @@
+/**
+ * Pre-push hook tests (T9). Builds a throwaway local "remote" + working repo,
+ * drives the hook with realistic stdin ref-lines, and checks: HIGH blocks,
+ * MEDIUM warns (non-blocking), correct remote..local diff direction, new-branch
+ * zero-SHA handling, branch-delete skip, escape valve, and hook chaining.
+ *
+ * We invoke bin/gstack-redact-prepush directly with the git pre-push stdin
+ * protocol rather than going through `git push`, which keeps the test fast and
+ * deterministic while exercising the exact code path git would.
+ */
+import { describe, test, expect, beforeEach, afterEach } from "bun:test";
+import * as fs from "fs";
+import * as os from "os";
+import * as path from "path";
+import { spawnSync } from "child_process";
+
+const PREPUSH = path.resolve(import.meta.dir, "..", "bin", "gstack-redact-prepush");
+const REDACT = path.resolve(import.meta.dir, "..", "bin", "gstack-redact");
+
+let repo: string;
+
+function git(args: string[], cwd = repo): string {
+  const r = spawnSync("git", args, { cwd, encoding: "utf8" });
+  return r.stdout?.trim() ?? "";
+}
+
+function commit(file: string, content: string, msg: string): string {
+  fs.writeFileSync(path.join(repo, file), content);
+  git(["add", file]);
+  git(["commit", "-q", "-m", msg]);
+  return git(["rev-parse", "HEAD"]);
+}
+
+function runHook(
+  stdinLines: string,
+  env: Record<string, string> = {},
+): { code: number; stderr: string } {
+  const r = spawnSync("bun", [PREPUSH], {
+    cwd: repo,
+    input: Buffer.from(stdinLines),
+    encoding: "utf8",
+    env: { ...process.env, ...env },
+  });
+  return { code: r.status ?? 0, stderr: r.stderr ?? "" };
+}
+
+const ZERO = "0000000000000000000000000000000000000000";
+
+beforeEach(() => {
+  repo = fs.mkdtempSync(path.join(os.tmpdir(), "prepush-"));
+  git(["init", "-q", "-b", "main"]);
+  git(["config", "user.email", "t@example.com"]);
+  git(["config", "user.name", "T"]);
+  commit("README.md", "hello\n", "init");
+});
+
+afterEach(() => {
+  fs.rmSync(repo, { recursive: true, force: true });
+});
+
+describe("pre-push hook gating", () => {
+  test("HIGH credential in pushed diff blocks (exit 1)", () => {
+    const base = git(["rev-parse", "HEAD"]);
+    const head = commit("config.txt", "key AKIA1234567890ABCDEF\n", "add key");
+    const { code, stderr } = runHook(`refs/heads/main ${head} refs/heads/main ${base}\n`);
+    expect(code).toBe(1);
+    expect(stderr).toContain("BLOCKED");
+    expect(stderr).toContain("aws.access_key");
+  });
+
+  test("clean diff passes (exit 0)", () => {
+    const base = git(["rev-parse", "HEAD"]);
+    const head = commit("doc.md", "just documentation\n", "add doc");
+    const { code } = runHook(`refs/heads/main ${head} refs/heads/main ${base}\n`);
+    expect(code).toBe(0);
+  });
+
+  test("MEDIUM warns but does not block", () => {
+    const base = git(["rev-parse", "HEAD"]);
+    const head = commit("notes.md", "contact bob@corp.io\n", "add note");
+    const { code, stderr } = runHook(`refs/heads/main ${head} refs/heads/main ${base}\n`);
+    expect(code).toBe(0);
+    expect(stderr).toContain("MEDIUM");
+  });
+});
+
+describe("diff direction + special refs", () => {
+  test("only NEW content is scanned (remote..local), not pre-existing", () => {
+    // Put a secret in the FIRST commit (already on remote), then push a clean commit.
+    const withSecret = commit("old.txt", "AKIA1234567890ABCDEF\n", "old secret already pushed");
+    const clean = commit("new.txt", "totally clean\n", "new clean commit");
+    // remote already has withSecret; we push only the clean commit on top.
+    const { code } = runHook(`refs/heads/main ${clean} refs/heads/main ${withSecret}\n`);
+    expect(code).toBe(0); // pre-existing secret is not in the pushed delta
+  });
+
+  test("new branch (zero remote sha) scans commits unique to the branch", () => {
+    const head = commit("feature.txt", "ghp_" + "a".repeat(36) + "\n", "feature with token");
+    const { code, stderr } = runHook(`refs/heads/feat ${head} refs/heads/feat ${ZERO}\n`);
+    expect(code).toBe(1);
+    expect(stderr).toContain("github.pat");
+  });
+
+  test("branch delete (zero local sha) is skipped", () => {
+    const { code } = runHook(`(delete) ${ZERO} refs/heads/old ${git(["rev-parse", "HEAD"])}\n`);
+    expect(code).toBe(0);
+  });
+});
+
+describe("escape valve", () => {
+  test("GSTACK_REDACT_PREPUSH=skip bypasses + logs", () => {
+    const base = git(["rev-parse", "HEAD"]);
+    const head = commit("config.txt", "key AKIA1234567890ABCDEF\n", "add key");
+    const home = fs.mkdtempSync(path.join(os.tmpdir(), "ghome-"));
+    const { code } = runHook(`refs/heads/main ${head} refs/heads/main ${base}\n`, {
+      GSTACK_REDACT_PREPUSH: "skip",
+      GSTACK_HOME: home,
+    });
+    expect(code).toBe(0);
+    const log = fs.readFileSync(path.join(home, "security", "prepush-skip.jsonl"), "utf8");
+    expect(log).toContain("env-skip");
+    fs.rmSync(home, { recursive: true, force: true });
+  });
+});
+
+describe("install / chaining", () => {
+  test("install creates a managed hook; existing hook preserved + chained", () => {
+    const hookDir = path.join(repo, ".git", "hooks");
+    fs.mkdirSync(hookDir, { recursive: true });
+    const existing = path.join(hookDir, "pre-push");
+    fs.writeFileSync(existing, "#!/usr/bin/env bash\necho mine\n", { mode: 0o755 });
+
+    const r = spawnSync("bun", [REDACT, "install-prepush-hook"], { cwd: repo, encoding: "utf8" });
+    expect(r.status).toBe(0);
+    const installed = fs.readFileSync(existing, "utf8");
+    expect(installed).toContain("gstack-redact pre-push (managed)");
+    expect(fs.existsSync(path.join(hookDir, "pre-push.local"))).toBe(true);
+    expect(fs.readFileSync(path.join(hookDir, "pre-push.local"), "utf8")).toContain("echo mine");
+  });
+
+  test("uninstall restores the chained original", () => {
+    const hookDir = path.join(repo, ".git", "hooks");
+    fs.mkdirSync(hookDir, { recursive: true });
+    fs.writeFileSync(path.join(hookDir, "pre-push"), "#!/usr/bin/env bash\necho mine\n", {
+      mode: 0o755,
+    });
+    spawnSync("bun", [REDACT, "install-prepush-hook"], { cwd: repo });
+    spawnSync("bun", [REDACT, "uninstall-prepush-hook"], { cwd: repo });
+    const restored = fs.readFileSync(path.join(hookDir, "pre-push"), "utf8");
+    expect(restored).toContain("echo mine");
+    expect(restored).not.toContain("managed");
+  });
+});