Core Rule Set: ls -la passes in q on a gitea user's or organisation's page (closes #349)

On a path of one segment, q now skips 932250 too, unless the path ends
in .php, as /index.php does. The Forgejo recording gains the two
searches for ls -la, made from the recorded searches for python3.

Model: opus-5-5

SPEC.md

@@ -828,20 +828,10 @@ The changes hold in front of every app, and no setting undoes them:
         - branches and tags;
         - packages, on its pages and in its API.
 
-        A user's or an organisation's page has a path of one segment, such as
-        `/alice`. So on any app, `q` skips these rules on every path of one
-        segment, such as `/search`. Such a path keeps 932250 when it ends in a
-        server-side script's extension, such as `/index.php`, so `ls -la` is
-        refused there. The extensions are these, in upper or lower case:
-        - `.php`;
-        - `.phtml`;
-        - `.php5`;
-        - `.cgi`;
-        - `.pl`;
-        - `.py`;
-        - `.asp`;
-        - `.aspx`;
-        - `.jsp`.
+        A user's or an organisation's page is any path of one segment, so on
+        every such path, on any app, `q` skips these rules, for example on
+        `/search`. A path that ends in `.php`, such as `/index.php`, keeps
+        932250, so `ls -la` is refused there.
 
         Some of these searches also skip the rule for Java class names (944130),
         which refused `org.apache.commons.logging`.

internal/coreruleset/coreruleset_test.go

@@ -1077,31 +1077,24 @@ func TestGiteaSearchOnAUsersOrAnOrganisationsPageLetsLsThrough(t *testing.T) {
 		wantResult(t, crs, get(target), coreruleset.Result{})
 	}
 
-	// 932250 still applies on a path that ends in a server-side script's
-	// extension, to another field, and on a path of two segments.
+	// A path that ends in .php, another field, and a path of two segments
+	// keep 932250.
 	for _, target := range []string{
 		"/index.php?q=ls%20-la",
 		"/INDEX.PHP?q=ls%20-la",
 		"/index%2Ephp?q=ls%20-la",
-		"/search.cgi?q=ls%20-la",
 		"/alice?tab=ls%20-la",
 		"/alice/tools?q=ls%20-la",
 	} {
 		wantResult(t, crs, get(target), matched(932250))
 	}
 
-	// A command after a ";" in q is still refused on each of these paths.
+	// A command after a ";" is still refused on those pages.
 	const threshold = 5 // SWW_WAF_ANOMALY_THRESHOLD's default
 
-	for _, target := range []string{
-		"/alice?tab=repositories&q=",
-		"/index.php?q=",
-		"/wp-login.php?q=",
-		"/alice/tools?q=",
-	} {
-		if got := inspect(t, crs, get(target+commandInjection)); got.Score < threshold {
-			t.Errorf("%s%s let through: %+v", target, commandInjection, got)
-		}
+	target := "/alice?tab=repositories&q=" + commandInjection
+	if got := inspect(t, crs, get(target)); got.Score < threshold {
+		t.Errorf("%s let through: %+v", target, got)
 	}
 }
 

internal/coreruleset/gitea.conf

@@ -146,11 +146,11 @@ SecRule REQUEST_FILENAME "@rx ^/[^/]+$" \
     ctl:ruleRemoveTargetById=932120;ARGS:q,\
     ctl:ruleRemoveTargetById=932260;ARGS:q"
 
-# On those pages q skips 932250 too, which refused ls -la. A path keeps it when
-# it ends in a server-side script's extension, such as /index.php or /search.cgi.
+# On those pages q skips 932250 too, which refused ls -la. A path that ends in
+# .php, such as /index.php, keeps it.
 SecRule REQUEST_FILENAME "@rx ^/[^/]+$" \
-    "id:900606,phase:1,pass,nolog,chain"
-    SecRule REQUEST_FILENAME "!@rx \.(?:php|phtml|php5|cgi|pl|py|asp|aspx|jsp)$" \
+    "id:900605,phase:1,pass,nolog,chain"
+    SecRule REQUEST_FILENAME "!@rx \.php$" \
         "t:lowercase,ctl:ruleRemoveTargetById=932250;ARGS:q"
 
 # These requests name a file in the path, which skips these rules there:

internal/coreruleset/testdata/forgejo-requests.txt

@@ -4,7 +4,9 @@
 # the API and the generic package registry, and by crane on the container
 # registry. Each line is one request as JSON. Names, addresses and passwords
 # are invented. The browser's User-Agent is an ordinary Chrome's. A body or a
-# multipart part that is not text is written as base64.
+# multipart part that is not text is written as base64. The searches for ls -la
+# on a user's and an organisation's page are the recorded searches for python3
+# there, with q changed.
 {"method": "GET", "target": "/", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate"], "body": ""}
 {"method": "GET", "target": "/assets/js/webcomponents.js?v=17.0.1~gitea-1.22.0", "headers": ["Host: example.com", "Connection: keep-alive", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: */*", "Referer: http://example.com/", "Accept-Encoding: gzip, deflate"], "body": ""}
 {"method": "GET", "target": "/assets/css/index.css?v=17.0.1~gitea-1.22.0", "headers": ["Host: example.com", "Connection: keep-alive", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/css,*/*;q=0.1", "Referer: http://example.com/", "Accept-Encoding: gzip, deflate"], "body": ""}
@@ -102,6 +104,7 @@
 {"method": "GET", "target": "/explore/users?q=python3", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/explore/organizations?q=python3", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/alice?tab=repositories&q=python3", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
+{"method": "GET", "target": "/alice?tab=repositories&q=ls%20-la", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/avatars/53bce4f1dfa0fe8e7ca126f91b35d3a6?size=64", "headers": ["Host: example.com", "Connection: keep-alive", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: image/jxl,image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8", "Referer: http://example.com/alice?tab=repositories&q=python3", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/alice/tools/commits/branch/main/search?q=python3&all=true", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/alice/-/packages?q=python3", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Accept-Encoding: gzip, deflate", "Cookie: session=d65379616ffd0971; lang=en-US"], "body": ""}
@@ -468,7 +471,4 @@
 {"method": "GET", "target": "/repo-avatars/f9e66d43eb4888aac5d9d93745661631a09b4c73969226a3e89b2911ece215ba", "headers": ["Host: example.com", "Connection: keep-alive", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: image/jxl,image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8", "Referer: http://example.com/alice", "Accept-Encoding: gzip, deflate", "Cookie: session=00a162ad65e95a87; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/avatars/53bce4f1dfa0fe8e7ca126f91b35d3a6?size=64", "headers": ["Host: example.com", "Connection: keep-alive", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: image/jxl,image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8", "Referer: http://example.com/alice", "Accept-Encoding: gzip, deflate", "Cookie: session=00a162ad65e95a87; lang=en-US"], "body": ""}
 {"method": "GET", "target": "/acme?q=python3&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/acme", "Accept-Encoding: gzip, deflate", "Cookie: session=00a162ad65e95a87; lang=en-US"], "body": ""}
-{"method": "GET", "target": "/alice?q=ls+-la&tab=repositories&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/alice?tab=repositories", "Accept-Encoding: gzip, deflate", "Cookie: session=4f05e01703d2563d; lang=en-US"], "body": ""}
-{"method": "GET", "target": "/acme?q=ls+-la&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/acme", "Accept-Encoding: gzip, deflate", "Cookie: session=4f05e01703d2563d; lang=en-US"], "body": ""}
-{"method": "GET", "target": "/acme?q=powershell&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/acme", "Accept-Encoding: gzip, deflate", "Cookie: session=4f05e01703d2563d; lang=en-US"], "body": ""}
-{"method": "GET", "target": "/acme?q=.htaccess&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/acme", "Accept-Encoding: gzip, deflate", "Cookie: session=4f05e01703d2563d; lang=en-US"], "body": ""}
+{"method": "GET", "target": "/acme?q=ls%20-la&sort=recentupdate", "headers": ["Host: example.com", "Connection: keep-alive", "Upgrade-Insecure-Requests: 1", "User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/156.0.8078.4 Safari/537.36", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", "Referer: http://example.com/acme", "Accept-Encoding: gzip, deflate", "Cookie: session=00a162ad65e95a87; lang=en-US"], "body": ""}

internal/coreruleset/testdata/gitea-requests.txt

@@ -91,17 +91,6 @@
 /explore/organizations?q=docker-ci
 /api/v1/users/search?q=docker-ci
 
-# Searches of the repositories on a user's and an organisation's page, recorded
-# from gitea 1.27.3.
-/alice?tab=repositories&q=ls+-la&sort=recentupdate
-/alice?tab=repositories&q=python3&sort=recentupdate
-/alice?tab=repositories&q=powershell&sort=recentupdate
-/alice?tab=repositories&q=.htaccess&sort=recentupdate
-/acme?q=ls+-la&sort=recentupdate
-/acme?q=python3&sort=recentupdate
-/acme?q=powershell&sort=recentupdate
-/acme?q=.htaccess&sort=recentupdate
-
 # Pages, raw files and edit pages of files, and the API's call for their
 # contents.
 /owner/repo/src/branch/main/package.json