v1.19.0-pre1

Signed-off-by: Xe Iaso <me@xeiaso.net>

.github/actions/spelling/expect.txt

@@ -178,6 +178,7 @@ selfsigned
 setsebool
 sitemap
 sls
+sni
 Sourceware
 Spambot
 sparkline
@@ -210,7 +211,7 @@ webmaster
 webpage
 websecure
 websites
-workaround
+Workaround
 workdir
 xcaddy
 Xeact

.github/actions/spelling/line_forbidden.patterns

@@ -20,9 +20,6 @@
 # https://twitter.com/nyttypos/status/1898844061873639490
 #\([A-Z][a-z]{2,}(?: [a-z]+){3,}\)\.\s
 
-# Complete sentences shouldn't be in the middle of another sentence as a parenthetical.
-(?<!\.)\.\),
-
 # Complete sentences in parentheticals should not have a space before the period.
 \s\.\)(?!.*\}\})
 

.github/actions/spelling/patterns.txt

@@ -128,3 +128,7 @@ go install(?:\s+[a-z]+\.[-@\w/.]+)+
 
 # ignore long runs of a single character:
 \b([A-Za-z])\g{-1}{3,}\b
+
+# hit-count: 1 file-count: 1
+# microsoft
+\b(?:https?://|)(?:(?:(?:blogs|download\.visualstudio|docs|msdn2?|research)\.|)microsoft|blogs\.msdn)\.co(?:m|\.\w\w)/[-_a-zA-Z0-9()=./%]*

VERSION

@@ -1 +1 @@
-1.18.0
+1.19.0-pre1

cmd/anubis/main.go

@@ -56,6 +56,7 @@ var (
 	redirectDomains          = flag.String("redirect-domains", "", "list of domains separated by commas which anubis is allowed to redirect to. Leaving this unset allows any domain.")
 	slogLevel                = flag.String("slog-level", "INFO", "logging level (see https://pkg.go.dev/log/slog#hdr-Levels)")
 	target                   = flag.String("target", "http://localhost:3923", "target to reverse proxy to, set to an empty string to disable proxying when only using auth request")
+	targetSNI                = flag.String("target-sni", "", "if set, the value of the TLS handshake hostname when forwarding requests to the target")
 	targetHost               = flag.String("target-host", "", "if set, the value of the Host header when forwarding requests to the target")
 	targetInsecureSkipVerify = flag.Bool("target-insecure-skip-verify", false, "if true, skips TLS validation for the backend")
 	healthcheck              = flag.Bool("healthcheck", false, "run a health check against Anubis")
@@ -136,7 +137,7 @@ func setupListener(network string, address string) (net.Listener, string) {
 	return listener, formattedAddress
 }
 
-func makeReverseProxy(target string, targetHost string, insecureSkipVerify bool) (http.Handler, error) {
+func makeReverseProxy(target string, targetSNI string, targetHost string, insecureSkipVerify bool) (http.Handler, error) {
 	targetUri, err := url.Parse(target)
 	if err != nil {
 		return nil, fmt.Errorf("failed to parse target URL: %w", err)
@@ -158,10 +159,14 @@ func makeReverseProxy(target string, targetHost string, insecureSkipVerify bool)
 		transport.RegisterProtocol("unix", libanubis.UnixRoundTripper{Transport: transport})
 	}
 
-	if insecureSkipVerify {
-		slog.Warn("TARGET_INSECURE_SKIP_VERIFY is set to true, TLS certificate validation will not be performed", "target", target)
-		transport.TLSClientConfig = &tls.Config{
-			InsecureSkipVerify: true,
+	if insecureSkipVerify || targetSNI != "" {
+		transport.TLSClientConfig = &tls.Config{}
+		if insecureSkipVerify {
+			slog.Warn("TARGET_INSECURE_SKIP_VERIFY is set to true, TLS certificate validation will not be performed", "target", target)
+			transport.TLSClientConfig.InsecureSkipVerify = true
+		}
+		if targetSNI != "" {
+			transport.TLSClientConfig.ServerName = targetSNI
 		}
 	}
 
@@ -214,7 +219,7 @@ func main() {
 	// when using anubis via Systemd and environment variables, then it is not possible to set targe to an empty string but only to space
 	if strings.TrimSpace(*target) != "" {
 		var err error
-		rp, err = makeReverseProxy(*target, *targetHost, *targetInsecureSkipVerify)
+		rp, err = makeReverseProxy(*target, *targetSNI, *targetHost, *targetInsecureSkipVerify)
 		if err != nil {
 			log.Fatalf("can't make reverse proxy: %v", err)
 		}

data/bots/ai-robots-txt.yaml

@@ -1,4 +1,4 @@
 - name: "ai-robots-txt"
   user_agent_regex: >-
-    AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|anthropic-ai|Applebot|Applebot-Extended|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo Bot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|NovaAct|OAI-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity-User|PerplexityBot|PetalBot|QualifiedBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot
+    AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|anthropic-ai|Applebot|Applebot-Extended|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-SearchBot|Claude-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google-CloudVertexBot|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo Bot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|MistralAI-User/1.0|NovaAct|OAI-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity-User|PerplexityBot|PetalBot|QualifiedBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio-Extended|wpbot|YouBot
   action: DENY

docs/docs/CHANGELOG.md

@@ -11,6 +11,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## v1.19.0: Jenomis cen Lexentale
+
+- Record if challenges were issued via the API or via embedded JSON in the challenge page HTML ([#531](https://github.com/TecharoHQ/anubis/issues/531))
 - Ensure that clients that are shown a challenge support storing cookies
 - Encode challenge pages with gzip level 1
 - Add `check-spelling` for spell checking
@@ -22,11 +25,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Ensure cookie renaming is consistent across configuration options
 - Add Bookstack app in data
 - Add `--target-host` flag/envvar to allow changing the value of the Host header in requests forwarded to the target service.
-- Bump AI-robots.txt to version 1.30 (add QualifiedBot)
+- Bump AI-robots.txt to version 1.31
 - Add `RuntimeDirectory` to systemd unit settings so native packages can listen over unix sockets
 - Added SearXNG instance tracker whitelist policy
 - Added Qualys SSL Labs whitelist policy
 - Fixed cookie deletion logic ([#520](https://github.com/TecharoHQ/anubis/issues/520), [#522](https://github.com/TecharoHQ/anubis/pull/522))
+- Add `--target-sni` flag/envvar to allow changing the value of the TLS handshake hostname in requests forwarded to the target service.
+- Fixed CEL expression matching validator to now properly error out when it receives empty expressions
 
 ## v1.18.0: Varis zos Galvus
 

docs/docs/admin/frameworks/wordpress.mdx

@@ -0,0 +1,39 @@
+# Wordpress
+
+Wordpress is the most popular blog engine on the planet.
+
+## Using a multi-site setup with Anubis
+
+If you have a multi-site setup where traffic goes through Anubis like this:
+
+```mermaid
+---
+title: Apache as tls terminator and HTTP router
+---
+
+flowchart LR
+    T(User Traffic)
+    subgraph Apache 2
+        TCP(TCP 80/443)
+        US(TCP 3001)
+    end
+
+    An(Anubis)
+    B(Backend)
+
+    T --> |TLS termination| TCP
+    TCP --> |Traffic filtering| An
+    An --> |Happy traffic| US
+    US --> |whatever you're doing| B
+```
+
+Wordpress may not realize that the underlying connection is being done over HTTPS. This could lead to a redirect loop in the `/wp-admin/` routes. In order to fix this, add the following to your `wp-config.php` file:
+
+```php
+if (isset($_SERVER['HTTP_X_FORWARDED_PROTO']) && $_SERVER['HTTP_X_FORWARDED_PROTO'] === 'https') {
+    $_SERVER['HTTPS'] = 'on';
+    $_SERVER['SERVER_PORT'] = 443;
+}
+```
+
+This will make Wordpress think that your connection is over HTTPS instead of plain HTTP.

docs/docs/admin/installation.mdx

@@ -84,6 +84,7 @@ If you don't know or understand what these settings mean, ignore them. These are
 
 | Environment Variable          | Default value | Explanation                                                                                                                                         |
 | :---------------------------- | :------------ | :-------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `TARGET_SNI`                  | unset         | If set, overrides the TLS handshake hostname in requests forwarded to `TARGET`.                                                                     |
 | `TARGET_HOST`                 | unset         | If set, overrides the Host header in requests forwarded to `TARGET`.                                                                                |
 | `TARGET_INSECURE_SKIP_VERIFY` | `false`       | If `true`, skip TLS certificate validation for targets that listen over `https`. If your backend does not listen over `https`, ignore this setting. |
 

docs/docs/admin/native-install.mdx

@@ -49,7 +49,7 @@ sudo install -D ./run/anubis@.service /etc/systemd/system
 Install the default configuration file to your system:
 
 ```text
-sudo install -D ./run/default.env /etc/anubis
+sudo install -D ./run/default.env /etc/anubis/default.env
 ```
 
   </TabItem>
@@ -77,6 +77,13 @@ Install Anubis with `rpm`:
 sudo rpm -ivh ./anubis-$VERSION.$ARCH.rpm
 ```
 
+  </TabItem>
+  <TabItem value="distro" label="Package managers">
+
+Some Linux distributions offer Anubis [as a native package](https://repology.org/project/anubis-anti-crawler/versions). If you want to install Anubis from your distribution's package manager, consult any upstream documentation for how to install the package. It will either be named `anubis`, `www-apps/anubis` or `www/anubis`.
+
+If you use a systemd-flavoured distribution, then follow the setup instructions for Debian or Red Hat Linux.
+
   </TabItem>
 </Tabs>
 

lib/anubis.go

@@ -31,10 +31,10 @@ import (
 )
 
 var (
-	challengesIssued = promauto.NewCounter(prometheus.CounterOpts{
+	challengesIssued = promauto.NewCounterVec(prometheus.CounterOpts{
 		Name: "anubis_challenges_issued",
 		Help: "The total number of challenges issued",
-	})
+	}, []string{"method"})
 
 	challengesValidated = promauto.NewCounter(prometheus.CounterOpts{
 		Name: "anubis_challenges_validated",
@@ -260,7 +260,7 @@ func (s *Server) MakeChallenge(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 	lg.Debug("made challenge", "challenge", challenge, "rules", rule.Challenge, "cr", cr)
-	challengesIssued.Inc()
+	challengesIssued.WithLabelValues("api").Inc()
 }
 
 func (s *Server) PassChallenge(w http.ResponseWriter, r *http.Request) {

lib/http.go

@@ -73,6 +73,7 @@ func (s *Server) RenderIndex(w http.ResponseWriter, r *http.Request, rule *polic
 		s.respondWithError(w, r, "Client Error: Please ensure your browser is up to date and try again later.")
 	}
 
+	challengesIssued.WithLabelValues("embedded").Add(1)
 	challenge := s.challengeFor(r, rule.Challenge.Difficulty)
 
 	var ogTags map[string]string = nil

lib/policy/config/config.go

@@ -224,7 +224,7 @@ func (is *ImportStatement) open() (fs.File, error) {
 func (is *ImportStatement) load() error {
 	fin, err := is.open()
 	if err != nil {
-		return fmt.Errorf("can't open %s: %w", is.Import, err)
+		return fmt.Errorf("%w: %s: %w", ErrInvalidImportStatement, is.Import, err)
 	}
 	defer fin.Close()
 

lib/policy/config/expressionorlist.go

@@ -54,6 +54,9 @@ func (eol *ExpressionOrList) UnmarshalJSON(data []byte) error {
 }
 
 func (eol *ExpressionOrList) Valid() error {
+	if eol.Expression == "" && len(eol.All) == 0 && len(eol.Any) == 0 {
+		return ErrExpressionEmpty
+	}
 	if len(eol.All) != 0 && len(eol.Any) != 0 {
 		return ErrExpressionCantHaveBoth
 	}

lib/policy/config/expressionorlist_test.go

@@ -51,6 +51,13 @@ func TestExpressionOrListUnmarshal(t *testing.T) {
 			}`,
 			validErr: ErrExpressionCantHaveBoth,
 		},
+		{
+			name: "expression-empty",
+			inp: `{
+			"any": []
+			}`,
+			validErr: ErrExpressionEmpty,
+		},
 	} {
 		t.Run(tt.name, func(t *testing.T) {
 			var eol ExpressionOrList

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@techaro/anubis",
-  "version": "1.18.0",
+  "version": "1.19.0-pre1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@techaro/anubis",
-      "version": "1.18.0",
+      "version": "1.19.0-pre1",
       "license": "ISC",
       "devDependencies": {
         "cssnano": "^7.0.7",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@techaro/anubis",
-  "version": "1.18.0",
+  "version": "1.19.0-pre1",
   "description": "",
   "main": "index.js",
   "scripts": {

web/static/robots.txt

@@ -9,6 +9,8 @@ User-agent: Brightbot 1.0
 User-agent: Bytespider
 User-agent: CCBot
 User-agent: ChatGPT-User
+User-agent: Claude-SearchBot
+User-agent: Claude-User
 User-agent: Claude-Web
 User-agent: ClaudeBot
 User-agent: cohere-ai
@@ -21,6 +23,7 @@ User-agent: FacebookBot
 User-agent: Factset_spyderbot
 User-agent: FirecrawlAgent
 User-agent: FriendlyCrawler
+User-agent: Google-CloudVertexBot
 User-agent: Google-Extended
 User-agent: GoogleOther
 User-agent: GoogleOther-Image
@@ -37,6 +40,7 @@ User-agent: meta-externalagent
 User-agent: Meta-ExternalAgent
 User-agent: meta-externalfetcher
 User-agent: Meta-ExternalFetcher
+User-agent: MistralAI-User/1.0
 User-agent: NovaAct
 User-agent: OAI-SearchBot
 User-agent: omgili
@@ -55,6 +59,7 @@ User-agent: TikTokSpider
 User-agent: Timpibot
 User-agent: VelenPublicWebCrawler
 User-agent: Webzio-Extended
+User-agent: wpbot
 User-agent: YouBot
 Disallow: /