Reduce false positives in safe PDF analysis (Adobe Reader behaviour)

data/malicioustlds.txt

@@ -0,0 +1,126 @@
+.link
+.cam
+.bar
+.surf
+.xyz
+.click
+.buzz
+.gq
+.ga
+.rest
+.ml
+.cc
+.cfd
+.cyou
+.accountant
+.ar
+.bg
+.bid
+.biz
+.biz.ua
+.br
+.camera
+.cf
+.club
+.co
+.co.ua
+.co.in
+.co.mz
+.co.nz
+.com.au
+.com.tw
+.computer
+.cricket
+.date
+.diet
+.download
+.email
+.es
+.faith
+.gdn
+.global
+.guru
+.help
+.in
+.info
+.kz
+.lol
+.loan
+.media
+.men
+.news
+.ninja
+.nyc
+.party
+.photography
+.pt
+.pw
+.racing
+.reise
+.review
+.rocks
+.ru
+.science
+.site
+.solutions
+.space
+.stream
+.tech
+.today
+.top
+.tr
+.trade
+.uno
+.us
+.vn
+.webcam
+.website
+.win
+.work
+.africa
+.autos
+.best
+.bet
+.bio
+.boats
+.bond
+.boston
+.boutique
+.center
+.charity
+.christmas
+.coupons
+.dance
+.finance
+.fishing
+.giving
+.hair
+.haus
+.homes
+.icu
+.kim
+.lat
+.llp
+.loans
+.love
+.ltd
+.mom
+.motorcycles
+.name
+.okinawa
+.promo
+.rehab
+.rugby
+.run
+.sale
+.sew
+.skin
+.store
+.sz
+.tattoo
+.tokyo
+.voto
+.wang
+.wf
+.yachts
+.you

modules/signatures/all/pdf_annot_urls.py

@@ -16,36 +16,69 @@
 from lib.cuckoo.common.abstracts import Signature
 
 
-class PDF_Annot_URLs(Signature):
-    name = "pdf_annot_urls"
-    description = "The PDF contains a Link Annotation to a compressed archive or executable file"
-    severity = 3
+class PDF_Annot_URLs_Checker(Signature):
+    name = "pdf_annot_urls_checker"
+    description = "The PDF contains a Link Annotation"
+    severity = 2  # Default severity
     categories = ["static"]
-    authors = ["Optiv"]
-    minimum = "1.3"
+    authors = ["Wassime BATTA"]
+    minimum = "0.5"
 
-    filter_analysistypes = set(["file"])
+    filter_analysistypes = set(["file","static"])
+
+    malicious_tlds_file = "/opt/CAPEv2/data/malicioustlds.txt"
+
+    def __init__(self, *args, **kwargs):
+        super(PDF_Annot_URLs_Checker, self).__init__(*args, **kwargs)
+        self.malicious_tlds = self.load_malicious_tlds()
+
+    def load_malicious_tlds(self):
+        malicious_tlds = set()
+        with open(self.malicious_tlds_file, "r") as f:
+            for line in f:
+                line = line.strip()
+                if line.startswith("."):
+                    malicious_tlds.add(line)
+        return malicious_tlds
 
     def run(self):
-        found_URLs = False
-        if "static" in self.results and "pdf" in self.results["static"]:
-            if "PDF" in self.results["target"]["file"].get("type", ""):
-                if "Annot_URLs" in self.results["static"]["pdf"]:
-                    for entry in self.results["static"]["pdf"]["Annot_URLs"]:
-                        entrylower = entry.lower()
-                        if entrylower.endswith(
-                            (".zip", ".exe", ".msi", ".bat", ".scr", ".rar", ".com")
-                        ) and not entrylower.startswith(
-                            "mailto:"
-                        ):  # skip mailto: as it can't add attachments
-                            skip = False
-                            # skip triggering on http:// and https:// links that don't have anything after the domain name
-                            # so http://foo.com will be skipped, but http://foo.com/malware.com will not be
-                            if entrylower.startswith("http://") and not entrylower.find("/", 8):
-                                skip = True
-                            elif entrylower.startswith("https://") and not entrylower.find("/", 9):
-                                skip = True
-                            if skip:
-                                self.data.append({"url": entry})
-                                found_URLs = True
-        return found_URLs
+        found_malicious_extension = False
+        found_malicious_domain = False
+        found_domain_only = False
+        suspect = False
+
+        if "PDF" in self.results["target"]["file"].get("type", ""):
+            if "Annot_URLs" in self.results["target"]["file"]["pdf"]:
+                for entry in self.results["target"]["file"]["pdf"]["Annot_URLs"]:
+                    entry_lower = entry.lower()
+                    self.data.append({"url": entry})
+                    if entry_lower.endswith((".exe", ".php", ".bat", ".cmd", ".js", ".jse", ".vbs", ".vbe", ".ps1", ".psm1", ".sh")) \
+                            and not entry_lower.startswith("mailto:"):
+                        found_malicious_extension = True
+
+                    if entry_lower.startswith("http://") or entry_lower.startswith("https://"):
+                        domain_start = entry_lower.find("//") + 2
+                        domain_end = entry_lower.find("/", domain_start)
+                        if domain_end == -1:
+                            domain = entry_lower[domain_start:]
+                        else:
+                            domain = entry_lower[domain_start:domain_end]
+
+                        for malicious_tld in self.malicious_tlds:
+                            if domain.endswith(malicious_tld):
+                                found_malicious_domain = True
+                                break
+                        else:
+                            # If no malicious TLDs detected, set found_domain_only to True
+                            found_domain_only = True
+
+            if found_malicious_domain or found_malicious_extension:
+                self.severity = 6
+                self.description = "The PDF contains a Malicious Link Annotation"
+                suspect = True
+            elif found_domain_only:
+                self.severity = 2
+                self.description = "The PDF contains a Link Annotation"
+                suspect = True
+
+        return suspect

modules/signatures/windows/credential_dumping.py

@@ -128,7 +128,9 @@ def run(self):
             if match:
                 self.data.append({"regkey": match})
                 ret = True
-
+        # Tweak
+        if "PDF" in self.results["target"]["file"].get("type", ""):
+            self.severity = 1
         return ret