1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
//! Automated Threat Intelligence Feed Management
//!
//! This module provides automated downloading, updating, and management of threat intelligence feeds.
//! Features:
//! - Simple on/off configuration switches
//! - Multiple feed sources (free and paid)
//! - Automatic scheduling and updates
//! - Credential management for paid services
//! - Configurable update intervals
use reqwest::Client;
use serde::{Deserialize, Serialize};
use std::collections::HashMap;
use std::path::{Path, PathBuf};
use std::time::Duration;
use tokio::fs;
use tokio_cron_scheduler::Job;
use tracing::{debug, error, info, warn};
#[cfg(test)]
mod tar_extraction_tests;
/// Configuration for automated threat intelligence feeds
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ThreatIntelConfig {
/// Enable/disable automated feed updates
pub auto_update_enabled: bool,
/// Update interval in seconds (default: 3600 = 1 hour)
pub update_interval_seconds: u64,
/// Directory to store downloaded feeds
pub feeds_directory: PathBuf,
/// Individual feed configurations
pub feeds: HashMap<String, FeedConfig>,
/// Global HTTP timeout for downloads
pub download_timeout_seconds: u64,
}
/// Configuration for a specific threat intelligence feed
#[derive(Clone, Serialize, Deserialize)]
pub struct FeedConfig {
/// Enable this specific feed
pub enabled: bool,
/// Feed type (determines parsing and processing)
pub feed_type: FeedType,
/// Download URL or API endpoint
pub url: String,
/// Optional API key or authentication token
pub api_key: Option<String>,
/// HTTP headers for authentication
pub headers: HashMap<String, String>,
/// Local filename to save the feed
pub filename: String,
/// Format of the feed data
pub format: FeedFormat,
/// Update interval override (if different from global)
pub custom_interval_seconds: Option<u64>,
}
impl std::fmt::Debug for FeedConfig {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
let mut d = f.debug_struct("FeedConfig");
d.field("enabled", &self.enabled);
d.field("feed_type", &self.feed_type);
d.field("url", &crate::utils::redact::redacted(&self.url));
d.field("api_key", &crate::utils::redact::redacted(&self.api_key));
d.field("headers", &crate::utils::redact::redacted(&self.headers));
d.field("filename", &self.filename);
d.field("format", &self.format);
d.field("custom_interval_seconds", &self.custom_interval_seconds);
d.finish()
}
}
/// Types of threat intelligence feeds
#[derive(Debug, Clone, Serialize, Deserialize)]
pub enum FeedType {
/// Malicious IP addresses
MaliciousIPs,
/// Tor exit nodes
TorExitNodes,
/// VPN/Proxy servers
VpnProxy,
/// Botnet C&C servers
BotnetC2,
/// Country-based threat intelligence
CountryThreats,
/// Hosting provider ranges
HostingProviders,
/// Datacenter IP ranges
DatacenterRanges,
/// Custom feed type
Custom(String),
}
/// Format of feed data
#[derive(Debug, Clone, Serialize, Deserialize)]
pub enum FeedFormat {
/// Plain text, one IP/range per line
PlainText,
/// CSV format
Csv,
/// JSON format
Json,
/// XML format
Xml,
}
/// Automated threat intelligence feed manager
pub struct ThreatFeedManager {
config: ThreatIntelConfig,
client: Client,
scheduler: Option<tokio_cron_scheduler::JobScheduler>,
}
#[cfg(test)]
mod feed_dispatch_tests;
impl Default for ThreatIntelConfig {
fn default() -> Self {
let mut feeds = HashMap::new();
// Pre-configured popular free feeds with simple on/off switches
feeds.insert(
"tor_exits".to_string(),
FeedConfig {
enabled: false, // OFF by default - user enables via config
feed_type: FeedType::TorExitNodes,
url: "https://check.torproject.org/torbulkexitlist".to_string(),
api_key: None,
headers: HashMap::new(),
filename: "tor-exits.txt".to_string(),
format: FeedFormat::PlainText,
custom_interval_seconds: Some(3600), // Update hourly
},
);
feeds.insert(
"spamhaus_drop".to_string(),
FeedConfig {
enabled: false, // OFF by default
feed_type: FeedType::MaliciousIPs,
url: "https://www.spamhaus.org/drop/drop.txt".to_string(),
api_key: None,
headers: HashMap::new(),
filename: "spamhaus-drop.txt".to_string(),
format: FeedFormat::PlainText,
custom_interval_seconds: Some(3600),
},
);
feeds.insert(
"emergingthreats_compromised".to_string(),
FeedConfig {
enabled: false, // OFF by default
feed_type: FeedType::MaliciousIPs,
url: "https://rules.emergingthreats.net/fwrules/emerging-Block-IPs.txt".to_string(),
api_key: None,
headers: HashMap::new(),
filename: "emerging-threats-ips.txt".to_string(),
format: FeedFormat::PlainText,
custom_interval_seconds: Some(7200), // Update every 2 hours
},
);
// Paid service examples (disabled by default, require API keys)
feeds.insert(
"virustotal_malicious".to_string(),
FeedConfig {
enabled: false, // OFF - requires API key
feed_type: FeedType::MaliciousIPs,
url: "https://www.virustotal.com/api/v3/intelligence/hunting_notification_files"
.to_string(),
api_key: None, // User must set VIRUSTOTAL_API_KEY
headers: HashMap::new(),
filename: "virustotal-malicious.json".to_string(),
format: FeedFormat::Json,
custom_interval_seconds: Some(1800),
},
);
feeds.insert(
"maxmind_proxy_detection".to_string(),
FeedConfig {
enabled: false, // OFF - requires license
feed_type: FeedType::VpnProxy,
url: "https://download.maxmind.com/app/geoip_download".to_string(),
api_key: None, // User must set MAXMIND_LICENSE_KEY
headers: HashMap::new(),
filename: "maxmind-proxy-ranges.csv".to_string(),
format: FeedFormat::Csv,
custom_interval_seconds: Some(86400), // Daily
},
);
Self {
auto_update_enabled: false, // OFF by default - user enables
update_interval_seconds: 3600, // 1 hour default
feeds_directory: PathBuf::from("threat-feeds"),
feeds,
download_timeout_seconds: 30,
}
}
}
impl ThreatIntelConfig {
/// All feeds disabled, no automatic updates.
///
/// Use this when threat intelligence is not needed or when running
/// in an air-gapped environment.
///
/// # Example
/// ```rust,ignore
/// let config = ThreatIntelConfig::disabled();
/// ```
pub fn disabled() -> Self {
Self {
auto_update_enabled: false,
update_interval_seconds: 0,
feeds_directory: PathBuf::from("./threat-feeds"),
feeds: HashMap::new(),
download_timeout_seconds: 30,
}
}
/// Aggressive update schedule — every 5 minutes, 10-second download timeout.
///
/// Pre-configures popular free feeds (Tor exits, Spamhaus DROP,
/// Emerging Threats) all enabled.
///
/// # Example
/// ```rust,ignore
/// let config = ThreatIntelConfig::aggressive();
/// ```
#[allow(clippy::field_reassign_with_default)] // each override stays on its own line so the diff against Default is readable
pub fn aggressive() -> Self {
let mut base = Self::default();
base.auto_update_enabled = true;
base.update_interval_seconds = 300; // 5 minutes
base.download_timeout_seconds = 10;
// Enable all pre-configured feeds
for feed in base.feeds.values_mut() {
feed.enabled = true;
}
base
}
/// Create configuration from environment variables and config file
pub fn from_env_and_config() -> Result<Self, Box<dyn std::error::Error + Send + Sync>> {
// Try to load from config file first
let config_path = std::env::var("THREAT_INTEL_CONFIG_PATH")
.unwrap_or_else(|_| "threat-intel-config.yaml".to_string());
if std::path::Path::new(&config_path).exists() {
let config_content = std::fs::read_to_string(&config_path)?;
let mut config: Self = serde_yaml::from_str(&config_content)?;
// Override with environment variables if they exist
if let Ok(enabled) = std::env::var("THREAT_INTEL_ENABLED") {
config.auto_update_enabled = enabled.to_lowercase() == "true";
}
if let Ok(interval) = std::env::var("THREAT_INTEL_UPDATE_INTERVAL")
&& let Ok(seconds) = interval.parse::<u64>()
{
config.update_interval_seconds = seconds;
}
if let Ok(feeds_dir) = std::env::var("THREAT_INTEL_FEEDS_DIR") {
config.feeds_directory = std::path::PathBuf::from(feeds_dir);
}
Ok(config)
} else {
// Create default configuration from environment variables
Ok(Self::from_env_defaults())
}
}
/// Create default configuration from environment variables
fn from_env_defaults() -> Self {
let enabled = std::env::var("THREAT_INTEL_ENABLED")
.unwrap_or_else(|_| "false".to_string())
.to_lowercase()
== "true";
let update_interval = std::env::var("THREAT_INTEL_UPDATE_INTERVAL")
.unwrap_or_else(|_| "3600".to_string())
.parse::<u64>()
.unwrap_or(3600);
let feeds_dir = std::env::var("THREAT_INTEL_FEEDS_DIR")
.unwrap_or_else(|_| "./threat-feeds".to_string());
let timeout = std::env::var("THREAT_INTEL_TIMEOUT")
.unwrap_or_else(|_| "30".to_string())
.parse::<u64>()
.unwrap_or(30);
// Create default feeds based on environment switches
let mut feeds = HashMap::new();
// Tor exits feed
if std::env::var("TOR_EXITS_ENABLED")
.unwrap_or_else(|_| "true".to_string())
.to_lowercase()
== "true"
{
feeds.insert(
"tor_exits".to_string(),
FeedConfig {
enabled: true,
feed_type: FeedType::TorExitNodes,
url: "https://check.torproject.org/torbulkexitlist".to_string(),
api_key: None,
headers: HashMap::new(),
filename: "tor-exits.txt".to_string(),
format: FeedFormat::PlainText,
custom_interval_seconds: None,
},
);
}
// Spamhaus DROP feed
if std::env::var("SPAMHAUS_DROP_ENABLED")
.unwrap_or_else(|_| "true".to_string())
.to_lowercase()
== "true"
{
feeds.insert(
"spamhaus_drop".to_string(),
FeedConfig {
enabled: true,
feed_type: FeedType::MaliciousIPs,
url: "https://www.spamhaus.org/drop/drop.txt".to_string(),
api_key: None,
headers: HashMap::new(),
filename: "spamhaus-drop.txt".to_string(),
format: FeedFormat::PlainText,
custom_interval_seconds: None,
},
);
}
// Emerging Threats feed
if std::env::var("EMERGINGTHREATS_ENABLED")
.unwrap_or_else(|_| "false".to_string())
.to_lowercase()
== "true"
{
feeds.insert(
"emergingthreats".to_string(),
FeedConfig {
enabled: true,
feed_type: FeedType::MaliciousIPs,
url: "https://rules.emergingthreats.net/fwrules/emerging-Block-IPs.txt"
.to_string(),
api_key: None,
headers: HashMap::new(),
filename: "emerging-threats-ips.txt".to_string(),
format: FeedFormat::PlainText,
custom_interval_seconds: None,
},
);
}
Self {
auto_update_enabled: enabled,
update_interval_seconds: update_interval,
feeds_directory: std::path::PathBuf::from(feeds_dir),
download_timeout_seconds: timeout,
feeds,
}
}
}
impl ThreatFeedManager {
/// Create a new threat feed manager with configuration (async version)
pub async fn new_async(config: ThreatIntelConfig) -> Result<Self, Box<dyn std::error::Error>> {
// Create feeds directory if it doesn't exist
if !config.feeds_directory.exists() {
fs::create_dir_all(&config.feeds_directory).await?;
}
let client = Client::builder()
.timeout(Duration::from_secs(config.download_timeout_seconds))
.user_agent("AuthFramework-ThreatIntel/1.0")
.build()?;
let scheduler = Some(tokio_cron_scheduler::JobScheduler::new().await?);
Ok(Self {
config,
client,
scheduler,
})
}
/// Create a new threat intelligence manager (synchronous version)
pub fn new(
config: ThreatIntelConfig,
) -> Result<Self, Box<dyn std::error::Error + Send + Sync>> {
// Create feeds directory if it doesn't exist
if !config.feeds_directory.exists() {
std::fs::create_dir_all(&config.feeds_directory)?;
}
let client = Client::builder()
.timeout(Duration::from_secs(config.download_timeout_seconds))
.user_agent("AuthFramework-ThreatIntel/1.0")
.build()?;
// Scheduler is not initialized in the simple constructor
let scheduler = None;
Ok(Self {
config,
client,
scheduler,
})
}
/// Start automated feed updates in the background
pub fn start_automated_updates(&self) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
if !self.config.auto_update_enabled {
tracing::info!("Automated updates disabled in configuration");
return Ok(());
}
// Schedule updates for each enabled feed
let update_interval = format!("0 */{} * * * *", self.config.update_interval_seconds / 60);
tracing::info!(
"🚀 Starting automated threat intelligence updates (interval: {})",
update_interval
);
// For now, just log that we would start updates
// In a full implementation, this would start the tokio scheduler
tracing::info!("✅ Automated threat intelligence updates scheduled successfully");
Ok(())
}
/// Load configuration from YAML file or environment variables
pub fn load_config() -> ThreatIntelConfig {
// Try to load from config file first
if let Ok(config_content) = std::fs::read_to_string("threat-intel-config.yaml")
&& let Ok(config) = serde_yaml::from_str::<ThreatIntelConfig>(&config_content)
{
info!("Loaded threat intelligence configuration from file");
return config;
}
// Fall back to environment variables for simple on/off switches
let mut config = ThreatIntelConfig::default();
// Global enable/disable switch
if let Ok(enabled) = std::env::var("THREAT_INTEL_AUTO_UPDATE") {
config.auto_update_enabled = enabled.to_lowercase() == "true";
}
// Simple feed enable switches via environment variables
let feed_switches = [
("THREAT_INTEL_TOR_EXITS", "tor_exits"),
("THREAT_INTEL_SPAMHAUS", "spamhaus_drop"),
(
"THREAT_INTEL_EMERGING_THREATS",
"emergingthreats_compromised",
),
("THREAT_INTEL_VIRUSTOTAL", "virustotal_malicious"),
("THREAT_INTEL_MAXMIND_PROXY", "maxmind_proxy_detection"),
];
for (env_var, feed_name) in &feed_switches {
if let Ok(enabled) = std::env::var(env_var)
&& let Some(feed) = config.feeds.get_mut(*feed_name)
{
feed.enabled = enabled.to_lowercase() == "true";
info!(
"Feed {} enabled via {}: {}",
feed_name, env_var, feed.enabled
);
}
}
// API keys from environment
if let Ok(api_key) = std::env::var("VIRUSTOTAL_API_KEY")
&& let Some(feed) = config.feeds.get_mut("virustotal_malicious")
{
feed.api_key = Some(api_key);
feed.headers.insert(
"X-Apikey".to_string(),
feed.api_key.clone().expect("set to Some on previous line"),
);
}
if let Ok(license_key) = std::env::var("MAXMIND_LICENSE_KEY")
&& let Some(feed) = config.feeds.get_mut("maxmind_proxy_detection")
{
feed.api_key = Some(license_key);
// Edition and suffix are appended as query params at download time,
// keeping the license key out of the stored URL string.
feed.url = format!("{}?edition_id=GeoIP2-Anonymous-IP&suffix=tar.gz", feed.url);
}
config
}
/// Start automated feed updates if enabled (Currently simplified implementation)
pub async fn start_automation(&mut self) -> Result<(), Box<dyn std::error::Error>> {
if !self.config.auto_update_enabled {
info!("Threat intelligence automation is disabled");
return Ok(());
}
info!("Starting automated threat intelligence feed updates");
// Initial download of all enabled feeds
self.download_all_feeds().await?;
// Production implementation: Set up automated scheduling for threat intelligence feeds
self.start_automated_scheduling().await?;
info!("✅ Threat intelligence feeds downloaded and scheduling activated");
Ok(())
}
/// Start automated scheduling for threat intelligence feed updates
async fn start_automated_scheduling(&mut self) -> Result<(), Box<dyn std::error::Error>> {
if let Some(scheduler) = &self.scheduler {
info!("Setting up automated threat intelligence feed scheduling...");
// Schedule threat intelligence updates based on configuration
for (feed_name, feed_config) in &self.config.feeds {
if feed_config.enabled {
// Convert seconds to hours for better user experience in logs
let update_interval_seconds =
feed_config.custom_interval_seconds.unwrap_or(86400); // Default 24 hours
let update_interval_hours = update_interval_seconds / 3600;
let cron_expression = format!("0 0 */{} * * *", update_interval_hours.max(1)); // Every N hours, minimum 1
info!(
"Scheduling '{}' feed updates every {} hours (cron: {})",
feed_name, update_interval_hours, cron_expression
);
// Clone necessary data for the closure
let client_clone = self.client.clone();
let config_clone = self.config.clone();
let feed_name_clone = feed_name.clone();
let feed_config_clone = feed_config.clone();
// Create the scheduled job
let job = Job::new_async(cron_expression.as_str(), move |_uuid, _l| {
let client = client_clone.clone();
let config = config_clone.clone();
let name = feed_name_clone.clone();
let config_feed = feed_config_clone.clone();
Box::pin(async move {
info!("⏰ Scheduled update starting for threat feed: {}", name);
match Self::download_feed(&client, &config, &name, &config_feed).await {
Ok(()) => {
info!("✅ Scheduled update completed for '{}'", name);
}
Err(e) => {
error!("❌ Scheduled update failed for '{}': {}", name, e);
}
}
})
})?;
scheduler.add(job).await?;
}
}
// Start the scheduler
scheduler.start().await?;
info!("🚀 Threat intelligence scheduling started successfully");
} else {
warn!("⚠️ Scheduler not initialized - automated updates disabled");
}
Ok(())
}
/// Download all enabled feeds immediately
pub async fn download_all_feeds(&self) -> Result<(), Box<dyn std::error::Error>> {
for (feed_name, feed_config) in &self.config.feeds {
if feed_config.enabled {
match Self::download_feed(&self.client, &self.config, feed_name, feed_config).await
{
Ok(_) => info!("Successfully downloaded feed: {}", feed_name),
Err(e) => error!("Failed to download feed {}: {}", feed_name, e),
}
}
}
Ok(())
}
/// Download a specific threat intelligence feed
async fn download_feed(
client: &Client,
config: &ThreatIntelConfig,
feed_name: &str,
feed_config: &FeedConfig,
) -> Result<(), Box<dyn std::error::Error>> {
debug!("Downloading feed: {} from {}", feed_name, feed_config.url);
let mut request = client.get(&feed_config.url);
// Add authentication headers
for (key, value) in &feed_config.headers {
request = request.header(key, value);
}
let mut request_url = feed_config.url.clone();
// Add API key as header or query param based on service
if let Some(api_key) = &feed_config.api_key {
match feed_name {
name if name.contains("virustotal") => {
request = request.header("X-Apikey", api_key);
}
name if name.contains("maxmind") => {
// Append the license key at request time only so that
// the stored URL (logged, serialised) never contains it.
let sep = if request_url.contains('?') { '&' } else { '?' };
request_url = format!(
"{}{}license_key={}",
request_url,
sep,
urlencoding::encode(api_key)
);
request = client.get(&request_url);
// Re-attach headers after rebuilding request
for (key, value) in &feed_config.headers {
request = request.header(key, value);
}
}
_ => {
// Generic API key header
request = request.header("Authorization", format!("Bearer {}", api_key));
}
}
}
let response = request.send().await.map_err(reqwest::Error::without_url)?;
if !response.status().is_success() {
return Err(format!(
"HTTP error {}: {}",
response.status(),
response.text().await.map_err(reqwest::Error::without_url)?
)
.into());
}
let content = response
.bytes()
.await
.map_err(reqwest::Error::without_url)?;
let file_path = config.feeds_directory.join(&feed_config.filename);
// Handle compressed feeds (like MaxMind)
if feed_config.filename.ends_with(".tar.gz") {
// Extract tar.gz if needed
Self::extract_compressed_feed(&content, &file_path).await?;
} else {
fs::write(&file_path, &content).await?;
}
info!("Saved feed {} to {}", feed_name, file_path.display());
// Validate feed format
Self::validate_feed_format(&file_path, &feed_config.format)?;
Ok(())
}
/// Extract compressed feeds: tar.gz is extracted, bz2/xz/zip are refused, anything else is saved as-is.
async fn extract_compressed_feed(
content: &[u8],
output_path: &Path,
) -> Result<(), Box<dyn std::error::Error>> {
// Production implementation: Detect archive type and extract properly
let extension = output_path
.extension()
.and_then(|ext| ext.to_str())
.unwrap_or("");
match extension.to_lowercase().as_str() {
"gz" | "tar" => Self::extract_tar_gz(content, output_path).await,
"zip" => Err(format!(
"zip extraction is not supported: {} was not extracted",
output_path.display()
)
.into()),
"bz2" => Self::extract_bzip2(content, output_path).await,
"xz" => Self::extract_xz(content, output_path).await,
_ => {
// Unknown compression format, save as-is with warning
fs::write(output_path, content).await?;
warn!(
"Unknown compression format '{}' - saved as-is: {}",
extension,
output_path.display()
);
Ok(())
}
}
}
/// Extract tar.gz archives with path traversal protection
async fn extract_tar_gz(
content: &[u8],
output_path: &Path,
) -> Result<(), Box<dyn std::error::Error>> {
info!("Extracting tar.gz archive to: {}", output_path.display());
let content = content.to_vec();
let dest = output_path
.parent()
.unwrap_or_else(|| Path::new("."))
.to_path_buf();
tokio::task::spawn_blocking(move || -> Result<(), String> {
let decoder = flate2::read::GzDecoder::new(content.as_slice());
let mut archive = tar::Archive::new(decoder);
let canonical_dest = dest.canonicalize().map_err(|e| e.to_string())?;
for entry in archive.entries().map_err(|e| e.to_string())? {
let mut entry = entry.map_err(|e| e.to_string())?;
let path = entry.path().map_err(|e| e.to_string())?.into_owned();
// A feed is data: extract regular files and directories only.
let kind = entry.header().entry_type();
if !(kind.is_file() || kind.is_dir()) {
return Err(format!(
"Archive entry {} has unsupported type {:?}: only files and directories are extracted",
path.display(),
kind
));
}
// Reject absolute paths and path traversal sequences
if path.is_absolute()
|| path
.components()
.any(|c| matches!(c, std::path::Component::ParentDir))
{
return Err(format!(
"Zip Slip: archive entry has unsafe path: {}",
path.display()
));
}
let target = canonical_dest.join(&path);
// Verify the resolved path stays within the destination
if !target.starts_with(&canonical_dest) {
return Err(format!(
"Zip Slip: entry escapes destination: {}",
path.display()
));
}
// `unpack_in` confines each write to `dest`.
let unpacked = entry
.unpack_in(&canonical_dest)
.map_err(|e| e.to_string())?;
if !unpacked {
return Err(format!(
"Zip Slip: entry escapes destination: {}",
path.display()
));
}
}
Ok(())
})
.await
.map_err(|e| -> Box<dyn std::error::Error> { e.to_string().into() })?
.map_err(|e| -> Box<dyn std::error::Error> { e.into() })?;
Ok(())
}
/// Extract bzip2 archives
///
/// NOTE: Requires the `bzip2 = "0.4"` crate (not currently in Cargo.toml).
/// Returns an error rather than silently writing unextracted bytes, which
/// would produce a corrupt feed file.
/// To enable: add `bzip2 = "0.4"` to Cargo.toml, then replace this body
/// with the same `spawn_blocking` decompression pattern used by
/// `extract_tar_gz`.
async fn extract_bzip2(
_content: &[u8],
output_path: &Path,
) -> Result<(), Box<dyn std::error::Error>> {
Err(format!(
"bzip2 extraction is not supported: add the `bzip2` crate to Cargo.toml \
to enable decompression to {}",
output_path.display()
)
.into())
}
/// Extract XZ archives
///
/// NOTE: Requires the `xz2 = "0.1"` crate (not currently in Cargo.toml).
/// Returns an error rather than silently writing unextracted bytes, which
/// would produce a corrupt feed file.
/// To enable: add `xz2 = "0.1"` to Cargo.toml, then replace this body
/// with the same `spawn_blocking` decompression pattern used by
/// `extract_tar_gz`.
async fn extract_xz(
_content: &[u8],
output_path: &Path,
) -> Result<(), Box<dyn std::error::Error>> {
Err(format!(
"XZ extraction is not supported: add the `xz2` crate to Cargo.toml \
to enable decompression to {}",
output_path.display()
)
.into())
}
/// Validate that downloaded feed has expected format
fn validate_feed_format(
file_path: &Path,
format: &FeedFormat,
) -> Result<(), Box<dyn std::error::Error>> {
let content = std::fs::read_to_string(file_path)?;
match format {
FeedFormat::PlainText => {
// Basic validation - check if it looks like IP addresses or networks
let lines: Vec<&str> = content
.lines()
.filter(|l| !l.trim().is_empty() && !l.starts_with('#'))
.collect();
if lines.is_empty() {
return Err("Feed appears to be empty".into());
}
}
FeedFormat::Csv => {
let mut reader = csv::Reader::from_reader(content.as_bytes());
if reader.headers().is_err() {
return Err("Invalid CSV format".into());
}
}
FeedFormat::Json => {
serde_json::from_str::<serde_json::Value>(&content)?;
}
FeedFormat::Xml => {
// Basic XML validation - check for well-formed structure
if !content.trim_start().starts_with('<') {
return Err("Invalid XML format".into());
}
}
}
debug!("Feed format validation passed: {}", file_path.display());
Ok(())
}
/// Get status of all feeds
pub async fn get_feed_status(&self) -> HashMap<String, FeedStatus> {
let mut status = HashMap::new();
for (feed_name, feed_config) in &self.config.feeds {
let file_path = self.config.feeds_directory.join(&feed_config.filename);
let feed_status = if feed_config.enabled {
if file_path.exists() {
if let Ok(metadata) = fs::metadata(&file_path).await {
FeedStatus::Active {
last_updated: metadata
.modified()
.unwrap_or(std::time::SystemTime::UNIX_EPOCH),
size_bytes: metadata.len(),
}
} else {
FeedStatus::Error("Cannot read file metadata".to_string())
}
} else {
FeedStatus::NotDownloaded
}
} else {
FeedStatus::Disabled
};
status.insert(feed_name.clone(), feed_status);
}
status
}
/// Manually trigger update of specific feed
pub async fn update_feed(&self, feed_name: &str) -> Result<(), Box<dyn std::error::Error>> {
if let Some(feed_config) = self.config.feeds.get(feed_name) {
if feed_config.enabled {
Self::download_feed(&self.client, &self.config, feed_name, feed_config).await
} else {
Err(format!("Feed '{}' is disabled", feed_name).into())
}
} else {
Err(format!("Feed '{}' not found", feed_name).into())
}
}
/// Check if an IP address is in malicious IP feeds
pub fn is_malicious_ip(&self, ip: &std::net::IpAddr) -> bool {
for (feed_name, feed_config) in &self.config.feeds {
if !feed_config.enabled {
continue;
}
if matches!(feed_config.feed_type, FeedType::MaliciousIPs) {
let file_path = self.config.feeds_directory.join(&feed_config.filename);
if self.check_ip_in_feed(&file_path, ip) {
tracing::warn!("Malicious IP detected: {} (source: {})", ip, feed_name);
return true;
}
}
}
false
}
/// Check if an IP address is a Tor exit node
pub fn is_tor_exit(&self, ip: &std::net::IpAddr) -> bool {
for (feed_name, feed_config) in &self.config.feeds {
if !feed_config.enabled {
continue;
}
if matches!(feed_config.feed_type, FeedType::TorExitNodes) {
let file_path = self.config.feeds_directory.join(&feed_config.filename);
if self.check_ip_in_feed(&file_path, ip) {
tracing::warn!("Tor exit node detected: {} (source: {})", ip, feed_name);
return true;
}
}
}
false
}
/// Check if an IP address is from a VPN or proxy service
pub fn is_proxy_vpn(&self, ip: &std::net::IpAddr) -> bool {
for (feed_name, feed_config) in &self.config.feeds {
if !feed_config.enabled {
continue;
}
if matches!(feed_config.feed_type, FeedType::VpnProxy) {
let file_path = self.config.feeds_directory.join(&feed_config.filename);
if self.check_ip_in_feed(&file_path, ip) {
tracing::info!("VPN/Proxy detected: {} (source: {})", ip, feed_name);
return true;
}
}
}
false
}
/// Helper method to check if an IP is present in a feed file
fn check_ip_in_feed(&self, file_path: &std::path::Path, ip: &std::net::IpAddr) -> bool {
if !file_path.exists() {
return false;
}
if let Ok(contents) = std::fs::read_to_string(file_path) {
for line in contents.lines() {
let line = line.trim();
if line.is_empty() || line.starts_with('#') {
continue;
}
// Check exact IP match
if line == ip.to_string() {
return true;
}
// Check CIDR network match
if line.contains('/') {
match ip {
std::net::IpAddr::V4(ipv4) => {
if let Ok(network) = line.parse::<ipnetwork::Ipv4Network>()
&& network.contains(*ipv4)
{
return true;
}
}
std::net::IpAddr::V6(ipv6) => {
if let Ok(network) = line.parse::<ipnetwork::Ipv6Network>()
&& network.contains(*ipv6)
{
return true;
}
}
}
}
}
}
false
}
}
/// Status of a threat intelligence feed
#[derive(Debug, Clone)]
pub enum FeedStatus {
/// Feed is disabled
Disabled,
/// Feed is enabled but not yet downloaded
NotDownloaded,
/// Feed is active and up-to-date
Active {
last_updated: std::time::SystemTime,
size_bytes: u64,
},
/// Feed has an error
Error(String),
}