Git tries not to distribute configs in-repo because they are a security
risk. However, an attacker can do exactly this if they embed a bare
repo inside of another repo.

Teach fsck to detect whether a tree object contains a bare repo (as
determined by setup.c) and warn. This will help hosting sites detect and
prevent transmission of such malicious repos.

See [1] for a more in-depth discussion, including future steps and
alternatives.

[1] https://lore.kernel.org/git/kl6lsfqpygsj.fsf@chooglen-macbookpro.roam.corp.google.com/

Signed-off-by: Glen Choo <chooglen@google.com>
---
 fsck.c          | 19 +++++++++++++++++++
 fsck.h          |  1 +
 setup.c         |  4 ++++
 t/t1450-fsck.sh | 36 ++++++++++++++++++++++++++++++++++++
 4 files changed, 60 insertions(+)

diff --git a/fsck.c b/fsck.c
index 3ec500d707..11c11c348a 100644
--- a/fsck.c
+++ b/fsck.c
@@ -573,6 +573,9 @@ static int fsck_tree(const struct object_id *tree_oid,
 	int has_bad_modes = 0;
 	int has_dup_entries = 0;
 	int not_properly_sorted = 0;
+	int has_head = 0;
+	int has_refs_entry = 0;
+	int has_objects_entry = 0;
 	struct tree_desc desc;
 	unsigned o_mode;
 	const char *o_name;
@@ -602,6 +605,12 @@ static int fsck_tree(const struct object_id *tree_oid,
 		has_dotdot |= !strcmp(name, "..");
 		has_dotgit |= is_hfs_dotgit(name) || is_ntfs_dotgit(name);
 		has_zero_pad |= *(char *)desc.buffer == '0';
+		has_head |= !strcasecmp(name, "HEAD")
+			&& (S_ISLNK(mode) || S_ISREG(mode));
+		has_refs_entry |= !strcasecmp(name, "refs")
+			&& (S_ISLNK(mode) || S_ISDIR(mode));
+		has_objects_entry |= !strcasecmp(name, "objects")
+			&& (S_ISLNK(mode) || S_ISDIR(mode));
 
 		if (is_hfs_dotgitmodules(name) || is_ntfs_dotgitmodules(name)) {
 			if (!S_ISLNK(mode))
@@ -739,6 +748,16 @@ static int fsck_tree(const struct object_id *tree_oid,
 		retval += report(options, tree_oid, OBJ_TREE,
 				 FSCK_MSG_TREE_NOT_SORTED,
 				 "not properly sorted");
+	/*
+	 * Determine if this tree looks like a bare repository according
+	 * to the rules of setup.c. If those are changed, this should be
+	 * changed too.
+	 */
+	if (has_head && has_refs_entry && has_objects_entry)
+		retval += report(options, tree_oid, OBJ_TREE,
+				 FSCK_MSG_EMBEDDED_BARE_REPO,
+				 "contains bare repository");
+
 	return retval;
 }
 
diff --git a/fsck.h b/fsck.h
index d07f7a2459..3f0f73b0f3 100644
--- a/fsck.h
+++ b/fsck.h
@@ -65,6 +65,7 @@ enum fsck_msg_type {
 	FUNC(NULL_SHA1, WARN) \
 	FUNC(ZERO_PADDED_FILEMODE, WARN) \
 	FUNC(NUL_IN_COMMIT, WARN) \
+	FUNC(EMBEDDED_BARE_REPO, WARN) \
 	/* infos (reported as warnings, but ignored by default) */ \
 	FUNC(GITMODULES_PARSE, INFO) \
 	FUNC(GITIGNORE_SYMLINK, INFO) \
diff --git a/setup.c b/setup.c
index 04ce33cdcd..2600548776 100644
--- a/setup.c
+++ b/setup.c
@@ -336,6 +336,10 @@ int get_common_dir_noenv(struct strbuf *sb, const char *gitdir)
  *  - either a HEAD symlink or a HEAD file that is formatted as
  *    a proper "ref:", or a regular file HEAD that has a properly
  *    formatted sha1 object name.
+ *
+ * fsck.c checks for bare repositories in trees using similar rules, but a
+ * duplicated implementation. If these are changed, the correspnding code in
+ * fsck.c should change too.
  */
 int is_git_directory(const char *suspect)
 {
diff --git a/t/t1450-fsck.sh b/t/t1450-fsck.sh
index de50c0ea01..a65827bc03 100755
--- a/t/t1450-fsck.sh
+++ b/t/t1450-fsck.sh
@@ -563,6 +563,42 @@ dot-backslash-case .\\\\.GIT\\\\foobar
 dotgit-case-backslash .git\\\\foobar
 EOF
 
+test_expect_success "fsck notices bare repo" '
+(
+	mkdir -p embedded-bare-repo/bare &&
+	git init embedded-bare-repo &&
+	(
+		cd embedded-bare-repo/bare &&
+		echo content >HEAD &&
+		mkdir refs/ objects/ &&
+		echo content >refs/foo &&
+		echo content >objects/foo &&
+		git add . &&
+		git commit -m base &&
+		bad_tree=$(git rev-parse HEAD:bare) &&
+		git fsck 2>out &&
+		test_i18ngrep "warning.*tree $bad_tree: embeddedBareRepo: contains bare repository" out
+	)
+)'
+
+test_expect_success "fsck notices bare repo with odd casing" '
+(
+	mkdir -p embedded-bare-repo-case/bare &&
+	git init embedded-bare-repo-case &&
+	(
+		cd embedded-bare-repo-case/bare &&
+		echo content >heAD &&
+		mkdir Refs/ objectS/ &&
+		echo content >Refs/foo &&
+		echo content >objectS/foo &&
+		git add . &&
+		git commit -m base &&
+		bad_tree=$(git rev-parse HEAD:bare) &&
+		git fsck 2>out &&
+		test_i18ngrep "warning.*tree $bad_tree: embeddedBareRepo: contains bare repository" out
+	)
+)'
+
 test_expect_success 'fsck allows .Ňit' '
 	(
 		git init not-dotgit &&

base-commit: 805e0a68082a217f0112db9ee86a022227a9c81b
-- 
2.33.GIT