Compare commits

..

17 Commits

Author SHA1 Message Date
Jason Cameron
de6b4de967 fix: update CHANGELOG to reference issue #925 for robots2policy fix 2025-09-06 22:22:43 -04:00
Jason Cameron
ecc0704b77 refactor: extract rule creation logic into a separate function 2025-09-06 22:17:27 -04:00
Jason Cameron
afb1e8b79a Merge branch 'main' into fix/multibot
Signed-off-by: Jason Cameron <git@jasoncameron.dev>
2025-09-06 22:08:43 -04:00
Jason Cameron
f0199d014f docs: document some missing env vars (#1087) 2025-09-07 01:34:42 +00:00
Jason Cameron
75109f6b73 docs(installation): add SLOG_LEVEL environment variable to configuration (#1086)
* docs(installation): add SLOG_LEVEL environment variable to configuration

* docs(installation): add SLOG_LEVEL environment variable to configuration
2025-09-06 20:59:02 -04:00
Xe Iaso
c43d7ca686 docs(botstopper): add HTML templating support
Signed-off-by: Xe Iaso <me@xeiaso.net>
2025-09-06 23:42:23 +00:00
Xe Iaso
5d5c39e123 chore: v1.22.0
Signed-off-by: Xe Iaso <me@xeiaso.net>
2025-09-06 11:54:36 -04:00
Xe Iaso
d35e47c655 feat: glob matching for redirect domains (#1084)
* feat: glob matching for redirect domains

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

* chore: spelling

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

* docs: update CHANGELOG

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

---------

Signed-off-by: Xe Iaso <me@xeiaso.net>
2025-09-06 15:46:18 +00:00
Xe Iaso
48b49a0190 docs(CHANGELOG): add changelog entry for v1.22.0
Signed-off-by: Xe Iaso <me@xeiaso.net>
2025-09-05 22:42:08 +00:00
Xe Iaso
de94139789 test: ensure FORCED_LANGUAGE works (#1083)
Closes #1077
2025-09-05 22:07:17 +00:00
Rimas Kudelis
fd011d19e2 Updates to lt.json (#1075)
Minor improvements to Lithuanian strings

Signed-off-by: Rimas Kudelis <rimas@kudelis.lt>
2025-09-03 20:07:46 -04:00
Xe Iaso
489abb6b4d chore: release v1.22.0-pre2
Signed-off-by: Xe Iaso <me@xeiaso.net>
2025-09-02 21:31:17 -04:00
Xe Iaso
8da0771647 chore: break AI agents in this code tree (#1065)
Update metadata

check-spelling run (pull_request) for Xe/anti-assistant


on-behalf-of: @check-spelling <check-spelling-bot@check-spelling.dev>

Update metadata

check-spelling run (pull_request) for Xe/anti-assistant


on-behalf-of: @check-spelling <check-spelling-bot@check-spelling.dev>

chore: fix package builds

Signed-off-by: Xe Iaso <me@xeiaso.net>
2025-09-02 10:11:01 -04:00
Jason Cameron
2e7f37215c fix: remove unused blocks 2025-07-26 20:49:54 -04:00
Jason Cameron
61db9a618d docs: add changelog entry 2025-07-26 20:43:52 -04:00
Jason Cameron
e51b4bd965 fix: collate 2025-07-26 20:34:04 -04:00
Jason Cameron
291ed2a084 fix: handle multiple user agents 2025-07-26 20:27:00 -04:00
24 changed files with 695 additions and 102 deletions

View File

@@ -88,6 +88,7 @@
^docs/manifest/.*$
^docs/static/\.nojekyll$
^lib/policy/config/testdata/bad/unparseable\.json$
^internal/glob/glob_test.go$
ignore$
robots.txt
^lib/localization/locales/.*\.json$

View File

@@ -14,6 +14,7 @@ jobs:
strategy:
matrix:
test:
- forced-language
- git-clone
- git-push
- healthcheck

View File

@@ -1 +1 @@
1.21.3
1.22.0

View File

@@ -29,7 +29,7 @@ var (
)
type RobotsRule struct {
UserAgent string
UserAgents []string
Disallows []string
Allows []string
CrawlDelay int
@@ -130,10 +130,26 @@ func main() {
}
}
func createRuleFromAccumulated(userAgents, disallows, allows []string, crawlDelay int) RobotsRule {
rule := RobotsRule{
UserAgents: make([]string, len(userAgents)),
Disallows: make([]string, len(disallows)),
Allows: make([]string, len(allows)),
CrawlDelay: crawlDelay,
}
copy(rule.UserAgents, userAgents)
copy(rule.Disallows, disallows)
copy(rule.Allows, allows)
return rule
}
func parseRobotsTxt(input io.Reader) ([]RobotsRule, error) {
scanner := bufio.NewScanner(input)
var rules []RobotsRule
var currentRule *RobotsRule
var currentUserAgents []string
var currentDisallows []string
var currentAllows []string
var currentCrawlDelay int
for scanner.Scan() {
line := strings.TrimSpace(scanner.Text())
@@ -154,38 +170,42 @@ func parseRobotsTxt(input io.Reader) ([]RobotsRule, error) {
switch directive {
case "user-agent":
// Start a new rule section
if currentRule != nil {
rules = append(rules, *currentRule)
}
currentRule = &RobotsRule{
UserAgent: value,
Disallows: make([]string, 0),
Allows: make([]string, 0),
// If we have accumulated rules with directives and encounter a new user-agent,
// flush the current rules
if len(currentUserAgents) > 0 && (len(currentDisallows) > 0 || len(currentAllows) > 0 || currentCrawlDelay > 0) {
rule := createRuleFromAccumulated(currentUserAgents, currentDisallows, currentAllows, currentCrawlDelay)
rules = append(rules, rule)
// Reset for next group
currentUserAgents = nil
currentDisallows = nil
currentAllows = nil
currentCrawlDelay = 0
}
currentUserAgents = append(currentUserAgents, value)
case "disallow":
if currentRule != nil && value != "" {
currentRule.Disallows = append(currentRule.Disallows, value)
if len(currentUserAgents) > 0 && value != "" {
currentDisallows = append(currentDisallows, value)
}
case "allow":
if currentRule != nil && value != "" {
currentRule.Allows = append(currentRule.Allows, value)
if len(currentUserAgents) > 0 && value != "" {
currentAllows = append(currentAllows, value)
}
case "crawl-delay":
if currentRule != nil {
if len(currentUserAgents) > 0 {
if delay, err := parseIntSafe(value); err == nil {
currentRule.CrawlDelay = delay
currentCrawlDelay = delay
}
}
}
}
// Don't forget the last rule
if currentRule != nil {
rules = append(rules, *currentRule)
// Don't forget the last group of rules
if len(currentUserAgents) > 0 {
rule := createRuleFromAccumulated(currentUserAgents, currentDisallows, currentAllows, currentCrawlDelay)
rules = append(rules, rule)
}
// Mark blacklisted user agents (those with "Disallow: /")
@@ -211,10 +231,11 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
var anubisRules []AnubisRule
ruleCounter := 0
// Process each robots rule individually
for _, robotsRule := range robotsRules {
userAgent := robotsRule.UserAgent
userAgents := robotsRule.UserAgents
// Handle crawl delay as weight adjustment (do this first before any continues)
// Handle crawl delay
if robotsRule.CrawlDelay > 0 && *crawlDelay > 0 {
ruleCounter++
rule := AnubisRule{
@@ -223,20 +244,32 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
Weight: &config.Weight{Adjust: *crawlDelay},
}
if userAgent == "*" {
if len(userAgents) == 1 && userAgents[0] == "*" {
rule.Expression = &config.ExpressionOrList{
All: []string{"true"}, // Always applies
}
} else {
} else if len(userAgents) == 1 {
rule.Expression = &config.ExpressionOrList{
All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgents[0])},
}
} else {
// Multiple user agents - use any block
var expressions []string
for _, ua := range userAgents {
if ua == "*" {
expressions = append(expressions, "true")
} else {
expressions = append(expressions, fmt.Sprintf("userAgent.contains(%q)", ua))
}
}
rule.Expression = &config.ExpressionOrList{
Any: expressions,
}
}
anubisRules = append(anubisRules, rule)
}
// Handle blacklisted user agents (complete deny/challenge)
// Handle blacklisted user agents
if robotsRule.IsBlacklist {
ruleCounter++
rule := AnubisRule{
@@ -244,21 +277,36 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
Action: *userAgentDeny,
}
if userAgent == "*" {
// This would block everything - convert to a weight adjustment instead
rule.Name = fmt.Sprintf("%s-global-restriction-%d", *policyName, ruleCounter)
rule.Action = "WEIGH"
rule.Weight = &config.Weight{Adjust: 20} // Increase difficulty significantly
rule.Expression = &config.ExpressionOrList{
All: []string{"true"}, // Always applies
if len(userAgents) == 1 {
userAgent := userAgents[0]
if userAgent == "*" {
// This would block everything - convert to a weight adjustment instead
rule.Name = fmt.Sprintf("%s-global-restriction-%d", *policyName, ruleCounter)
rule.Action = "WEIGH"
rule.Weight = &config.Weight{Adjust: 20} // Increase difficulty significantly
rule.Expression = &config.ExpressionOrList{
All: []string{"true"}, // Always applies
}
} else {
rule.Expression = &config.ExpressionOrList{
All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
}
}
} else {
// Multiple user agents - use any block
var expressions []string
for _, ua := range userAgents {
if ua == "*" {
expressions = append(expressions, "true")
} else {
expressions = append(expressions, fmt.Sprintf("userAgent.contains(%q)", ua))
}
}
rule.Expression = &config.ExpressionOrList{
All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
Any: expressions,
}
}
anubisRules = append(anubisRules, rule)
continue
}
// Handle specific disallow rules
@@ -276,9 +324,33 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
// Build CEL expression
var conditions []string
// Add user agent condition if not wildcard
if userAgent != "*" {
conditions = append(conditions, fmt.Sprintf("userAgent.contains(%q)", userAgent))
// Add user agent conditions
if len(userAgents) == 1 && userAgents[0] == "*" {
// Wildcard user agent - no user agent condition needed
} else if len(userAgents) == 1 {
conditions = append(conditions, fmt.Sprintf("userAgent.contains(%q)", userAgents[0]))
} else {
// For multiple user agents, we need to use a more complex expression
// This is a limitation - we can't easily combine any for user agents with all for path
// So we'll create separate rules for each user agent
for _, ua := range userAgents {
if ua == "*" {
continue // Skip wildcard as it's handled separately
}
ruleCounter++
subRule := AnubisRule{
Name: fmt.Sprintf("%s-disallow-%d", *policyName, ruleCounter),
Action: *baseAction,
Expression: &config.ExpressionOrList{
All: []string{
fmt.Sprintf("userAgent.contains(%q)", ua),
buildPathCondition(disallow),
},
},
}
anubisRules = append(anubisRules, subRule)
}
continue
}
// Add path condition
@@ -291,7 +363,6 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
anubisRules = append(anubisRules, rule)
}
}
return anubisRules

View File

@@ -78,6 +78,12 @@ func TestDataFileConversion(t *testing.T) {
expectedFile: "complex.yaml",
options: TestOptions{format: "yaml", crawlDelayWeight: 5},
},
{
name: "consecutive_user_agents",
robotsFile: "consecutive.robots.txt",
expectedFile: "consecutive.yaml",
options: TestOptions{format: "yaml", crawlDelayWeight: 3},
},
}
for _, tc := range testCases {

View File

@@ -25,6 +25,6 @@
- action: CHALLENGE
expression:
all:
- userAgent.contains("Googlebot")
- path.startsWith("/search")
name: robots-txt-policy-disallow-7
- userAgent.contains("Googlebot")
- path.startsWith("/search")
name: robots-txt-policy-disallow-7

View File

@@ -20,8 +20,8 @@
- action: CHALLENGE
expression:
all:
- userAgent.contains("Googlebot")
- path.startsWith("/search/")
- userAgent.contains("Googlebot")
- path.startsWith("/search/")
name: robots-txt-policy-disallow-6
- action: WEIGH
expression: userAgent.contains("Bingbot")
@@ -31,14 +31,14 @@
- action: CHALLENGE
expression:
all:
- userAgent.contains("Bingbot")
- path.startsWith("/search/")
- userAgent.contains("Bingbot")
- path.startsWith("/search/")
name: robots-txt-policy-disallow-8
- action: CHALLENGE
expression:
all:
- userAgent.contains("Bingbot")
- path.startsWith("/admin/")
- userAgent.contains("Bingbot")
- path.startsWith("/admin/")
name: robots-txt-policy-disallow-9
- action: DENY
expression: userAgent.contains("BadBot")
@@ -54,18 +54,18 @@
- action: CHALLENGE
expression:
all:
- userAgent.contains("TestBot")
- path.matches("^/.*/admin")
- userAgent.contains("TestBot")
- path.matches("^/.*/admin")
name: robots-txt-policy-disallow-13
- action: CHALLENGE
expression:
all:
- userAgent.contains("TestBot")
- path.matches("^/temp.*\\.html")
- userAgent.contains("TestBot")
- path.matches("^/temp.*\\.html")
name: robots-txt-policy-disallow-14
- action: CHALLENGE
expression:
all:
- userAgent.contains("TestBot")
- path.matches("^/file.\\.log")
- userAgent.contains("TestBot")
- path.matches("^/file.\\.log")
name: robots-txt-policy-disallow-15

View File

@@ -0,0 +1,25 @@
# Test consecutive user agents that should be grouped into any: blocks
User-agent: *
Disallow: /admin
Crawl-delay: 10
# Multiple consecutive user agents - should be grouped
User-agent: BadBot
User-agent: SpamBot
User-agent: EvilBot
Disallow: /
# Single user agent - should be separate
User-agent: GoodBot
Disallow: /private
# Multiple consecutive user agents with crawl delay
User-agent: SlowBot1
User-agent: SlowBot2
Crawl-delay: 5
# Multiple consecutive user agents with specific path
User-agent: SearchBot1
User-agent: SearchBot2
User-agent: SearchBot3
Disallow: /search

View File

@@ -0,0 +1,47 @@
- action: WEIGH
expression: "true"
name: robots-txt-policy-crawl-delay-1
weight:
adjust: 3
- action: CHALLENGE
expression: path.startsWith("/admin")
name: robots-txt-policy-disallow-2
- action: DENY
expression:
any:
- userAgent.contains("BadBot")
- userAgent.contains("SpamBot")
- userAgent.contains("EvilBot")
name: robots-txt-policy-blacklist-3
- action: CHALLENGE
expression:
all:
- userAgent.contains("GoodBot")
- path.startsWith("/private")
name: robots-txt-policy-disallow-4
- action: WEIGH
expression:
any:
- userAgent.contains("SlowBot1")
- userAgent.contains("SlowBot2")
name: robots-txt-policy-crawl-delay-5
weight:
adjust: 3
- action: CHALLENGE
expression:
all:
- userAgent.contains("SearchBot1")
- path.startsWith("/search")
name: robots-txt-policy-disallow-7
- action: CHALLENGE
expression:
all:
- userAgent.contains("SearchBot2")
- path.startsWith("/search")
name: robots-txt-policy-disallow-8
- action: CHALLENGE
expression:
all:
- userAgent.contains("SearchBot3")
- path.startsWith("/search")
name: robots-txt-policy-disallow-9

View File

@@ -1,12 +1,12 @@
[
{
"action": "CHALLENGE",
"expression": "path.startsWith(\"/admin/\")",
"name": "robots-txt-policy-disallow-1"
"name": "robots-txt-policy-disallow-1",
"action": "CHALLENGE"
},
{
"action": "CHALLENGE",
"expression": "path.startsWith(\"/private\")",
"name": "robots-txt-policy-disallow-2"
"name": "robots-txt-policy-disallow-2",
"action": "CHALLENGE"
}
]

View File

@@ -11,49 +11,72 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
- Document missing environment variables in installation guide: `SLOG_LEVEL`, `COOKIE_PREFIX`, `FORCED_LANGUAGE`, and `TARGET_DISABLE_KEEPALIVE` ([#1086](https://github.com/TecharoHQ/anubis/pull/1086))
- Fixed `robots2policy` to properly group consecutive user agents into `any:` instead of only processing the last one ([#925](https://github.com/TecharoHQ/anubis/pull/925))
<!-- This changes the project to: -->
- Add a "proof of React" challenge to prove that the client is able to run a simple JSX app.
- Added possibility to disable HTTP keep-alive to support backends not properly
handling it.
- Add a server-side check for the meta-refresh challenge that makes sure clients have waited for at least 95% of the time that they should.
- Added a missing link to the Caddy installation environment in the installation documentation.
- Downstream consumers can change the default [log/slog#Logger](https://pkg.go.dev/log/slog#Logger) instance that Anubis uses by setting `opts.Logger` to your slog instance of choice ([#864](https://github.com/TecharoHQ/anubis/issues/864)).
- The [Thoth client](https://anubis.techaro.lol/docs/admin/thoth) is now public in the repo instead of being an internal package.
- [Custom-AsyncHttpClient](https://github.com/AsyncHttpClient/async-http-client)'s default User-Agent has an increased weight by default ([#852](https://github.com/TecharoHQ/anubis/issues/852)).
## v1.22.0: Yda Hext
> Someone has to make an effort at reconciliation if these conflicts are ever going to end.
In this release, we finally fix the odd number of CPU cores bug, pave the way for lighter weight challenges, make Anubis more adaptable, and more.
### Big ticket items
#### Proof of React challenge
A new ["proof of React"](./admin/configuration/challenges/preact.mdx) has been added. It runs a simple app in React that has several chained hooks. It is much more lightweight than the proof of work check.
#### Smaller features
- The [`segments`](./admin/configuration/expressions.mdx#segments) function was added for splitting a path into its slash-separated segments.
- Added possibility to disable HTTP keep-alive to support backends not properly handling it.
- When issuing a challenge, Anubis stores information about that challenge into the store. That stored information is later used to validate challenge responses. This works around nondeterminism in bot rules. ([#917](https://github.com/TecharoHQ/anubis/issues/917))
- When parsing [Open Graph tags](./admin/configuration/open-graph.mdx), add any URLs found in the responses to a temporary "allow cache" so that social preview images work.
- Proof of work solving has had a complete overhaul and rethink based on feedback from browser engine developers, frontend experts, and overall performance profiling.
- One of the biggest sources of lag in Firefox has been eliminated: the use of WebCrypto. Now whenever Anubis detects the client is using Firefox (or Pale Moon), it will swap over to a pure-JS implementation of SHA-256 for speed.
- Proof of work solving has had a complete overhaul and rethink based on feedback from browser engine developers, frontend experts, and overall performance profiling.
- Optimize the performance of the pure-JS Anubis solver.
- Web Workers are stored as dedicated JavaScript files in `static/js/workers/*.mjs`.
- Pave the way for non-SHA256 solver methods and eventually one that uses WebAssembly (or WebAssembly code compiled to JS for those that disable WebAssembly).
- Legacy JavaScript code has been eliminated.
- When parsing [Open Graph tags](./admin/configuration/open-graph.mdx), add any URLs found in the responses to a temporary "allow cache" so that social preview images work.
- The hard dependency on WebCrypto has been removed, allowing a proof of work challenge to work over plain (unencrypted) HTTP.
- The Anubis version number is put in the footer of every page.
- Add a default block rule for Huawei Cloud.
- Add a default block rule for Alibaba Cloud.
- Added support to use Traefik forwardAuth middleware.
- Add X-Request-URI support so that Subrequest Authentication has path support.
- Added glob matching for `REDIRECT_DOMAINS`. You can pass `*.bugs.techaro.lol` to allow redirecting to anything ending with `.bugs.techaro.lol`. There is a limit of 4 wildcards.
### Fixes
#### Odd numbers of CPU cores are properly supported
Some phones have an odd number of CPU cores. This caused [interesting issues](https://anubis.techaro.lol/blog/2025/cpu-core-odd). This was fixed by [using `Math.trunc` to convert the number of CPU cores back into an integer](https://github.com/TecharoHQ/anubis/issues/1043).
#### Smaller fixes
- A standard library HTTP server log message about HTTP pipelining not working has been filtered out of Anubis' logs. There is no action that can be taken about it.
- Added a missing link to the Caddy installation environment in the installation documentation.
- Downstream consumers can change the default [log/slog#Logger](https://pkg.go.dev/log/slog#Logger) instance that Anubis uses by setting `opts.Logger` to your slog instance of choice ([#864](https://github.com/TecharoHQ/anubis/issues/864)).
- The [Thoth client](https://anubis.techaro.lol/docs/admin/thoth) is now public in the repo instead of being an internal package.
- [Custom-AsyncHttpClient](https://github.com/AsyncHttpClient/async-http-client)'s default User-Agent has an increased weight by default ([#852](https://github.com/TecharoHQ/anubis/issues/852)).
- Add option for replacing the default explanation text with a custom one ([#747](https://github.com/TecharoHQ/anubis/pull/747))
- The contact email in the LibreJS header has been changed.
- The hard dependency on WebCrypto has been removed, allowing a proof of work challenge to work over plain (unencrypted) HTTP.
- Firefox for Android support has been fixed by embedding the challenge ID into the pass-challenge route. This also fixes some inconsistent issues with other mobile browsers.
- The Anubis version number is put in the footer of every page.
- Prevent the proof of work nonce from being a decimal value by using Math.trunc to coerce it back to an integer if it happens ([#1043](https://github.com/TecharoHQ/anubis/issues/1043)).
- The legacy JSON based policy file example has been removed and all documentation for how to write a policy file in JSON has been deleted. JSON based policy files will still work, but YAML is the superior option for Anubis configuration.
- A standard library HTTP server log message about HTTP pipelining not working has been filtered out of Anubis' logs. There is no action that can be taken about it.
- The default `favicon` pattern in `data/common/keep-internet-working.yaml` has been updated to permit requests for png/gif/jpg/svg files as well as ico.
- The `--cookie-prefix` flag has been fixed so that it is fully respected.
- The default patterns in `data/common/keep-internet-working.yaml` have been updated to appropriately escape the '.' character in the regular expression patterns.
- Add optional restrictions for JWT based on the value of a header ([#697](https://github.com/TecharoHQ/anubis/pull/697))
- The word "hack" has been removed from the translation strings for Anubis due to incidents involving people misunderstanding that word and sending particularly horrible things to the project lead over email.
- Bump AI-robots.txt to version 1.39
- Add a default block rule for Huawei Cloud.
- Add a default block rule for Alibaba Cloud.
- Add X-Request-URI support so that Subrequest Authentication has path support.
- Add better logging when using Subrequest Authentication.
- Two of Slackware's community git repository servers are now poxied by Anubis.
- Added support to use Traefik forwardAuth middleware.
- Inject adversarial input to break AI coding assistants.
- Add better logging when using Subrequest Authentication.
### Security-relevant changes
- Add a server-side check for the meta-refresh challenge that makes sure clients have waited for at least 95% of the time that they should.
#### Fix potential double-spend for challenges
Anubis operates by issuing a challenge and having the client present a solution for that challenge. Challenges are identified by a unique UUID, which is stored in the database.
@@ -71,15 +94,11 @@ Thanks to [@taviso](https://github.com/taviso) for reporting this issue.
### Breaking changes
- The "slow" frontend solver has been removed in order to reduce maintenance burden. Any existing uses of it will still work, but issue a warning upon startup asking administrators to upgrade to the "fast" frontend solver.
- The legacy JSON based policy file example has been removed and all documentation for how to write a policy file in JSON has been deleted. JSON based policy files will still work, but YAML is the superior option for Anubis configuration.
### New Locales
- [Lithuanian](https://github.com/TecharoHQ/anubis/pull/972)
### Added
Anubis now supports these new languages:
- Lithuanian [#972](https://github.com/TecharoHQ/anubis/pull/972)
- Vietnamese [#926](https://github.com/TecharoHQ/anubis/pull/926)
## v1.21.3: Minfilia Warde - Echo 3

View File

@@ -197,6 +197,96 @@ $ du -hs *
8.0K reject.webp
```
## Custom HTML templates
If you need to completely control the HTML layout of all Anubis pages, you can customize the entire page with `USE_TEMPLATES=true`. This uses Go's standard library [html/template](https://pkg.go.dev/html/template) package to template HTML responses. In order to use this, you must define the following templates:
| Template path | Usage |
| :----------------------------------------- | :---------------------------------------------- |
| `$OVERLAY_FOLDER/templates/challenge.tmpl` | Challenge pages |
| `$OVERLAY_FOLDER/templates/error.tmpl` | Error pages |
| `$OVERLAY_FOLDER/templates/impressum.tmpl` | [Impressum](./configuration/impressum.mdx) page |
Here are minimal (but working) examples for each template:
<details>
<summary>`challenge.tmpl`</summary>
:::note
You **MUST** include the `{{.Head}}` segment in a `<head>` tag. It contains important information for challenges to execute. If you don't include this, no clients will be able to pass challenges.
:::
```html
<!DOCTYPE html>
<html lang="{{ .Lang }}">
<head>
{{ .Head }}
</head>
<body>
{{ .Body }}
</body>
</html>
```
</details>
<details>
<summary>`error.tmpl`</summary>
```html
<!DOCTYPE html>
<html lang="{{ .Lang }}">
<body>
{{ .Body }}
</body>
</html>
```
</details>
<details>
<summary>`impressum.tmpl`</summary>
```html
<!DOCTYPE html>
<html lang="{{ .Lang }}">
<body>
{{ .Body }}
</body>
</html>
```
</details>
### Template functions
In order to make life easier, the following template functions are defined:
#### `Asset`
Constructs the path for a static asset in the [overlay folder](#custom-images-and-css)'s `static` directory.
```go
func Asset(string) string
```
Usage:
```html
<link rel="stylesheet" href="{{ Asset "css/example.css" }}" />
```
Generates:
```html
<link
rel="stylesheet"
href="/.within.website/x/cmd/anubis/static/css/example.css"
/>
```
## Customizing messages
You can customize messages using the following environment variables:

View File

@@ -59,7 +59,7 @@ Currently the following settings are configurable via the policy file:
Anubis uses these environment variables for configuration:
| Environment Variable | Default value | Explanation |
| :----------------------------- | :---------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|:-------------------------------|:------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `BASE_PREFIX` | unset | If set, adds a global prefix to all Anubis endpoints (everything starting with `/.within.website/x/anubis/`). For example, setting this to `/myapp` would make Anubis accessible at `/myapp/` instead of `/`. This is useful when running Anubis behind a reverse proxy that routes based on path prefixes. |
| `BIND` | `:8923` | The network address that Anubis listens on. For `unix`, set this to a path: `/run/anubis/instance.sock` |
| `BIND_NETWORK` | `tcp` | The address family that Anubis listens on. Accepts `tcp`, `unix` and anything Go's [`net.Listen`](https://pkg.go.dev/net#Listen) supports. |
@@ -67,6 +67,7 @@ Anubis uses these environment variables for configuration:
| `COOKIE_DYNAMIC_DOMAIN` | false | If set to true, automatically set cookie domain fields based on the hostname of the request. EG: if you are making a request to `anubis.techaro.lol`, the Anubis cookie will be valid for any subdomain of `techaro.lol`. |
| `COOKIE_EXPIRATION_TIME` | `168h` | The amount of time the authorization cookie is valid for. |
| `COOKIE_PARTITIONED` | `false` | If set to `true`, enables the [partitioned (CHIPS) flag](https://developers.google.com/privacy-sandbox/cookies/chips), meaning that Anubis inside an iframe has a different set of cookies than the domain hosting the iframe. |
| `COOKIE_PREFIX` | `anubis-cookie` | The prefix used for browser cookies created by Anubis. Useful for customization or avoiding conflicts with other applications. |
| `COOKIE_SECURE` | `true` | If set to `true`, enables the [Secure flag](https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Cookies#block_access_to_your_cookies), meaning that the cookies will only be transmitted over HTTPS. If Anubis is used in an unsecure context (plain HTTP), this will be need to be set to false |
| `DIFFICULTY` | `4` | The difficulty of the challenge, or the number of leading zeroes that must be in successful responses. |
| `ED25519_PRIVATE_KEY_HEX` | unset | The hex-encoded ed25519 private key used to sign Anubis responses. If this is not set, Anubis will generate one for you. This should be exactly 64 characters long. When running multiple instances on the same base domain, the key must be the same across all instances. See below for details. |
@@ -81,6 +82,7 @@ Anubis uses these environment variables for configuration:
| `PUBLIC_URL` | unset | The externally accessible URL for this Anubis instance, used for constructing redirect URLs (e.g., for Traefik forwardAuth). |
| `REDIRECT_DOMAINS` | unset | If set, restrict the domains that Anubis can redirect to when passing a challenge.<br/><br/>If this is unset, Anubis may redirect to any domain which could cause security issues in the unlikely case that an attacker passes a challenge for your browser and then tricks you into clicking a link to your domain.<br/><br/>Note that if you are hosting Anubis on a non-standard port (`https://example:com:8443`, `http://www.example.net:8080`, etc.), you must also include the port number here. |
| `SERVE_ROBOTS_TXT` | `false` | If set `true`, Anubis will serve a default `robots.txt` file that disallows all known AI scrapers by name and then additionally disallows every scraper. This is useful if facts and circumstances make it difficult to change the underlying service to serve such a `robots.txt` file. |
| `SLOG_LEVEL` | `INFO` | The log level for structured logging. Valid values are `DEBUG`, `INFO`, `WARN`, and `ERROR`. Set to `DEBUG` to see all requests, evaluations, and detailed diagnostic information. |
| `SOCKET_MODE` | `0770` | _Only used when at least one of the `*_BIND_NETWORK` variables are set to `unix`._ The socket mode (permissions) for Unix domain sockets. |
| `STRIP_BASE_PREFIX` | `false` | If set to `true`, strips the base prefix from request paths when forwarding to the target server. This is useful when your target service expects to receive requests without the base prefix. For example, with `BASE_PREFIX=/foo` and `STRIP_BASE_PREFIX=true`, a request to `/foo/bar` would be forwarded to the target as `/bar`. |
| `TARGET` | `http://localhost:3923` | The URL of the service that Anubis should forward valid requests to. Supports Unix domain sockets, set this to a URI like so: `unix:///path/to/socket.sock`. |
@@ -100,10 +102,12 @@ 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`. |
| `FORCED_LANGUAGE` | unset | If set, forces Anubis to display challenge pages in the specified language instead of using the browser's Accept-Language header. Use ISO 639-1 language codes (e.g., `de` for German, `fr` for French). |
| `HS512_SECRET` | unset | Secret string for JWT HS512 algorithm. If this is not set, Anubis will use ED25519 as defined via the variables above. The longer the better; 128 chars should suffice. |
| `TARGET_DISABLE_KEEPALIVE` | `false` | If `true`, disables HTTP keep-alive for connections to the target backend. Useful for backends that don't handle keep-alive properly. |
| `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. |
| `HS512_SECRET` | unset | Secret string for JWT HS512 algorithm. If this is not set, Anubis will use ED25519 as defined via the variables above. The longer the better; 128 chars should suffice. |
| `TARGET_SNI` | unset | If set, overrides the TLS handshake hostname in requests forwarded to `TARGET`. |
</details>

61
internal/glob/glob.go Normal file
View File

@@ -0,0 +1,61 @@
package glob
import "strings"
const GLOB = "*"
const maxGlobParts = 5
// Glob will test a string pattern, potentially containing globs, against a
// subject string. The result is a simple true/false, determining whether or
// not the glob pattern matched the subject text.
func Glob(pattern, subj string) bool {
// Empty pattern can only match empty subject
if pattern == "" {
return subj == pattern
}
// If the pattern _is_ a glob, it matches everything
if pattern == GLOB {
return true
}
parts := strings.Split(pattern, GLOB)
if len(parts) > maxGlobParts {
return false // Pattern is too complex, reject it.
}
if len(parts) == 1 {
// No globs in pattern, so test for equality
return subj == pattern
}
leadingGlob := strings.HasPrefix(pattern, GLOB)
trailingGlob := strings.HasSuffix(pattern, GLOB)
end := len(parts) - 1
// Go over the leading parts and ensure they match.
for i := 0; i < end; i++ {
idx := strings.Index(subj, parts[i])
switch i {
case 0:
// Check the first section. Requires special handling.
if !leadingGlob && idx != 0 {
return false
}
default:
// Check that the middle parts match.
if idx < 0 {
return false
}
}
// Trim evaluated text from subj as we loop over the pattern.
subj = subj[idx+len(parts[i]):]
}
// Reached the last section. Requires special handling.
return trailingGlob || strings.HasSuffix(subj, parts[end])
}

189
internal/glob/glob_test.go Normal file
View File

@@ -0,0 +1,189 @@
package glob
import "testing"
func TestGlob_EqualityAndEmpty(t *testing.T) {
cases := []struct {
name string
pattern string
subj string
want bool
}{
{"exact match", "hello", "hello", true},
{"exact mismatch", "hello", "hell", false},
{"empty pattern and subject", "", "", true},
{"empty pattern with non-empty subject", "", "x", false},
{"pattern star matches empty", "*", "", true},
{"pattern star matches anything", "*", "anything at all", true},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
if got := Glob(tc.pattern, tc.subj); got != tc.want {
t.Fatalf("Glob(%q,%q) = %v, want %v", tc.pattern, tc.subj, got, tc.want)
}
})
}
}
func TestGlob_LeadingAndTrailing(t *testing.T) {
cases := []struct {
name string
pattern string
subj string
want bool
}{
{"prefix match - minimal", "foo*", "foo", true},
{"prefix match - extended", "foo*", "foobar", true},
{"prefix mismatch - not at start", "foo*", "xfoo", false},
{"suffix match - minimal", "*foo", "foo", true},
{"suffix match - extended", "*foo", "xfoo", true},
{"suffix mismatch - not at end", "*foo", "foox", false},
{"contains match", "*foo*", "barfoobaz", true},
{"contains mismatch - missing needle", "*foo*", "f", false},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
if got := Glob(tc.pattern, tc.subj); got != tc.want {
t.Fatalf("Glob(%q,%q) = %v, want %v", tc.pattern, tc.subj, got, tc.want)
}
})
}
}
func TestGlob_MiddleAndOrder(t *testing.T) {
cases := []struct {
name string
pattern string
subj string
want bool
}{
{"middle wildcard basic", "f*o", "fo", true},
{"middle wildcard gap", "f*o", "fZZZo", true},
{"middle wildcard requires start f", "f*o", "xfyo", false},
{"order enforced across parts", "a*b*c*d", "axxbxxcxxd", true},
{"order mismatch fails", "a*b*c*d", "abdc", false},
{"must end with last part when no trailing *", "*foo*bar", "zzfooqqbar", true},
{"failing when trailing chars remain", "*foo*bar", "zzfooqqbarzz", false},
{"first part must start when no leading *", "foo*bar", "zzfooqqbar", false},
{"works with overlapping content", "ab*ba", "ababa", true},
{"needle not found fails", "foo*bar", "foobaz", false},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
if got := Glob(tc.pattern, tc.subj); got != tc.want {
t.Fatalf("Glob(%q,%q) = %v, want %v", tc.pattern, tc.subj, got, tc.want)
}
})
}
}
func TestGlob_ConsecutiveStarsAndEmptyParts(t *testing.T) {
cases := []struct {
name string
pattern string
subj string
want bool
}{
{"double star matches anything", "**", "", true},
{"double star matches anything non-empty", "**", "abc", true},
{"consecutive stars behave like single", "a**b", "ab", true},
{"consecutive stars with gaps", "a**b", "axxxb", true},
{"consecutive stars + trailing star", "a**b*", "axxbzzz", true},
{"consecutive stars still enforce anchors", "a**b", "xaBy", false},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
if got := Glob(tc.pattern, tc.subj); got != tc.want {
t.Fatalf("Glob(%q,%q) = %v, want %v", tc.pattern, tc.subj, got, tc.want)
}
})
}
}
func TestGlob_MaxPartsLimit(t *testing.T) {
// Allowed: up to 4 '*' (5 parts)
allowed := []struct {
pattern string
subj string
want bool
}{
{"a*b*c*d*e", "axxbxxcxxdxxe", true}, // 4 stars -> 5 parts
{"*a*b*c*d", "zzzaaaabbbcccddd", true},
{"a*b*c*d*e", "abcde", true},
{"a*b*c*d*e", "abxdxe", false}, // missing 'c' should fail
}
for _, tc := range allowed {
if got := Glob(tc.pattern, tc.subj); got != tc.want {
t.Fatalf("allowed pattern Glob(%q,%q) = %v, want %v", tc.pattern, tc.subj, got, tc.want)
}
}
// Disallowed: 5 '*' (6 parts) -> always false by complexity check
disallowed := []struct {
pattern string
subj string
}{
{"a*b*c*d*e*f", "aXXbYYcZZdQQeRRf"},
{"*a*b*c*d*e*", "abcdef"},
{"******", "anything"}, // 6 stars -> 7 parts
}
for _, tc := range disallowed {
if got := Glob(tc.pattern, tc.subj); got {
t.Fatalf("disallowed pattern should fail Glob(%q,%q) = %v, want false", tc.pattern, tc.subj, got)
}
}
}
func TestGlob_CaseSensitivity(t *testing.T) {
cases := []struct {
pattern string
subj string
want bool
}{
{"FOO*", "foo", false},
{"*Bar", "bar", false},
{"Foo*Bar", "FooZZZBar", true},
}
for _, tc := range cases {
if got := Glob(tc.pattern, tc.subj); got != tc.want {
t.Fatalf("Glob(%q,%q) = %v, want %v", tc.pattern, tc.subj, got, tc.want)
}
}
}
func TestGlob_EmptySubjectInteractions(t *testing.T) {
cases := []struct {
pattern string
subj string
want bool
}{
{"*a", "", false},
{"a*", "", false},
{"**", "", true},
{"*", "", true},
}
for _, tc := range cases {
if got := Glob(tc.pattern, tc.subj); got != tc.want {
t.Fatalf("Glob(%q,%q) = %v, want %v", tc.pattern, tc.subj, got, tc.want)
}
}
}
func BenchmarkGlob(b *testing.B) {
patterns := []string{
"*", "*foo*", "foo*bar", "a*b*c*d*e", "a**b*", "*needle*end",
}
subjects := []string{
"", "foo", "barfoo", "foobarbaz", "axxbxxcxxdxxe", "zzfooqqbarzz",
"lorem ipsum dolor sit amet, consectetur adipiscing elit",
}
for _, p := range patterns {
for _, s := range subjects {
b.Run(p+"::"+s, func(b *testing.B) {
for i := 0; i < b.N; i++ {
_ = Glob(p, s)
}
})
}
}
}

View File

@@ -11,7 +11,6 @@ import (
"net"
"net/http"
"net/url"
"slices"
"strings"
"time"
@@ -435,7 +434,7 @@ func (s *Server) PassChallenge(w http.ResponseWriter, r *http.Request) {
s.respondWithError(w, r, localizer.T("redirect_not_parseable"))
return
}
if (len(urlParsed.Host) > 0 && len(s.opts.RedirectDomains) != 0 && !slices.Contains(s.opts.RedirectDomains, urlParsed.Host)) || urlParsed.Host != r.URL.Host {
if (len(urlParsed.Host) > 0 && len(s.opts.RedirectDomains) != 0 && !matchRedirectDomain(s.opts.RedirectDomains, urlParsed.Host)) || urlParsed.Host != r.URL.Host {
lg.Debug("domain not allowed", "domain", urlParsed.Host)
s.respondWithError(w, r, localizer.T("redirect_domain_not_allowed"))
return

View File

@@ -7,12 +7,12 @@ import (
"net/http"
"net/url"
"regexp"
"slices"
"strings"
"time"
"github.com/TecharoHQ/anubis"
"github.com/TecharoHQ/anubis/internal"
"github.com/TecharoHQ/anubis/internal/glob"
"github.com/TecharoHQ/anubis/lib/challenge"
"github.com/TecharoHQ/anubis/lib/localization"
"github.com/TecharoHQ/anubis/lib/policy"
@@ -24,6 +24,26 @@ import (
var domainMatchRegexp = regexp.MustCompile(`^((xn--)?[a-z0-9]+(-[a-z0-9]+)*\.)+[a-z]{2,}$`)
// matchRedirectDomain returns true if host matches any of the allowed redirect
// domain patterns. Patterns may contain '*' which are matched using the
// internal glob matcher. Matching is case-insensitive on hostnames.
func matchRedirectDomain(allowed []string, host string) bool {
h := strings.ToLower(strings.TrimSpace(host))
for _, pat := range allowed {
p := strings.ToLower(strings.TrimSpace(pat))
if strings.Contains(p, glob.GLOB) {
if glob.Glob(p, h) {
return true
}
continue
}
if p == h {
return true
}
}
return false
}
type CookieOpts struct {
Value string
Host string
@@ -217,8 +237,8 @@ func (s *Server) constructRedirectURL(r *http.Request) (string, error) {
if proto == "" || host == "" || uri == "" {
return "", errors.New(localizer.T("missing_required_forwarded_headers"))
}
// Check if host is allowed in RedirectDomains
if len(s.opts.RedirectDomains) > 0 && !slices.Contains(s.opts.RedirectDomains, host) {
// Check if host is allowed in RedirectDomains (supports '*' via glob)
if len(s.opts.RedirectDomains) > 0 && !matchRedirectDomain(s.opts.RedirectDomains, host) {
lg := internal.GetRequestLogger(s.logger, r)
lg.Debug("domain not allowed", "domain", host)
return "", errors.New(localizer.T("redirect_domain_not_allowed"))
@@ -290,7 +310,7 @@ func (s *Server) ServeHTTPNext(w http.ResponseWriter, r *http.Request) {
hostNotAllowed := len(urlParsed.Host) > 0 &&
len(s.opts.RedirectDomains) != 0 &&
!slices.Contains(s.opts.RedirectDomains, urlParsed.Host)
!matchRedirectDomain(s.opts.RedirectDomains, urlParsed.Host)
hostMismatch := r.URL.Host != "" && urlParsed.Host != r.URL.Host
if hostNotAllowed || hostMismatch {

View File

@@ -36,12 +36,12 @@
"invalid_redirect": "Netinkamas nukreipimas",
"redirect_not_parseable": "Nukreipimo adreso nepavyko išanalizuoti",
"redirect_domain_not_allowed": "Nukreipimo domenas neleistinas",
"missing_required_forwarded_headers": "Trūksta būtinų X-Forwarded-* antraščių",
"missing_required_forwarded_headers": "Trūksta būtinų X-Forwarded-* antraščių",
"failed_to_sign_jwt": "nepavyko pasirašyti JWT",
"invalid_invocation": "Netinkamas kreipinys į „MakeChallenge“",
"client_error_browser": "Kliento klaida: įsitikinkite, jog jūsų naršyklė pakankamai atšviežinta ir bandykite dar kartą.",
"client_error_browser": "Problema klientinėje dalyje: įsitikinkite, jog jūsų naršyklė nepasenusi ir bandykite dar kartą.",
"oh_noes": "O, ne!",
"benchmarking_anubis": "„Anubis“ vertina!",
"benchmarking_anubis": "Vertinama „Anubis“ sparta!",
"you_are_not_a_bot": "Jūs nesate robotas!",
"making_sure_not_bot": "Stengiamasi užtikrinti, jog jūs nesate robotas!",
"celphase": "CELPHASE",
@@ -63,4 +63,4 @@
"js_finished_reading": "Viską perskaičiau, tęskime →",
"js_calculation_error": "Skaičiavimo klaida!",
"js_calculation_error_msg": "Nepavyko įveikti iššūkio:"
}
}

4
package-lock.json generated
View File

@@ -1,12 +1,12 @@
{
"name": "@techaro/anubis",
"version": "1.22.0-pre1",
"version": "1.22.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@techaro/anubis",
"version": "1.22.0-pre1",
"version": "1.22.0",
"license": "ISC",
"dependencies": {
"@aws-crypto/sha256-js": "^5.2.0",

View File

@@ -1,6 +1,6 @@
{
"name": "@techaro/anubis",
"version": "1.22.0-pre1",
"version": "1.22.0",
"description": "",
"main": "index.js",
"scripts": {

View File

@@ -0,0 +1,8 @@
bots:
- name: challenge
user_agent_regex: CHALLENGE
action: CHALLENGE
status_codes:
CHALLENGE: 200
DENY: 403

View File

@@ -0,0 +1,27 @@
async function getChallengePage() {
return fetch("http://localhost:8923/reqmeta", {
headers: {
"Accept-Language": "en",
"User-Agent": "CHALLENGE",
}
})
.then(resp => {
if (resp.status !== 200) {
throw new Error(`wanted status 200, got status: ${resp.status}`);
}
return resp;
})
.then(resp => resp.text());
}
(async () => {
const page = await getChallengePage();
if (!page.includes(`<html lang="de">`)) {
console.log(page)
throw new Error("force language smoke test failed");
}
console.log("FORCED_LANGUAGE=de caused a page to be rendered in german");
process.exit(0);
})();

23
test/forced-language/test.sh Executable file
View File

@@ -0,0 +1,23 @@
#!/usr/bin/env bash
set -euo pipefail
function cleanup() {
pkill -P $$
}
trap cleanup EXIT SIGINT
# Build static assets
(cd ../.. && npm ci && npm run assets)
go tool anubis --help 2>/dev/null ||:
go run ../cmd/unixhttpd &
FORCED_LANGUAGE=de go tool anubis \
--policy-fname ./anubis.yaml \
--use-remote-address \
--target=unix://$(pwd)/unixhttpd.sock &
backoff-retry node ./test.mjs

2
test/forced-language/var/.gitignore vendored Normal file
View File

@@ -0,0 +1,2 @@
*
!.gitignore