fixing issues with mailto links and parameter extraction

blacklanternsecurity · Dec 19, 2024 · f8a8e8d · f8a8e8d
1 parent 42eebcd
commit f8a8e8d
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/bbot/core/helpers/regexes.py b/bbot/core/helpers/regexes.py
@@ -140,7 +140,7 @@
 textarea_tag_regex = re.compile(
     r'<textarea[^>]*\bname=["\']?(\w+)["\']?[^>]*>(.*?)</textarea>', re.IGNORECASE | re.DOTALL
 )
-tag_attribute_regex = re.compile(r"<[^>]*(?:href|src)\s*=\s*[\"\']([^\"\']+)[\"\'][^>]*>")
+tag_attribute_regex = re.compile(r"<[^>]*(?:href|action|src)\s*=\s*[\"\']?(?!mailto:)([^\s\'\"\>]+)[\"\']?[^>]*>")
 
 valid_netloc = r"[^\s!@#$%^&()=/?\\'\";~`<>]+"