mcp-server-semgrep/semgrep-rules/scala/lang/security/audit/documentbuilder-dtd-enabled.yaml

MCP Server for Semgrep Integration - static code analysis with AI

rules:
- id: documentbuilder-dtd-enabled
  patterns:
  - pattern-either:
    - pattern: |
        $DF = DocumentBuilderFactory.newInstance(...)
        ...
        $DB = $DF.newDocumentBuilder(...)
    - patterns:
      - pattern: $DB = DocumentBuilderFactory.newInstance(...)
      - pattern-not-inside: |
          ...
          $X = $DB.newDocumentBuilder(...)
    - pattern: $DB = DocumentBuilderFactory.newInstance(...).newDocumentBuilder(...)
  - pattern-not-inside: | # nosemgrep: slow-pattern-top-ellipsis
      ...
      $DB.setXIncludeAware(true)
      ...
      $DB.setNamespaceAware(true)
      ...
      $DB.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true)
      ...
      $DB.setFeature("http://xml.org/sax/features/external-general-entities", false)
      ...
      $DB.setFeature("http://xml.org/sax/features/external-parameter-entities", false)
  - pattern-not-inside: | # nosemgrep: slow-pattern-top-ellipsis
      ...
      $DB.setXIncludeAware(true)
      ...
      $DB.setNamespaceAware(true)
      ...
      $DB.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true)
      ...
      $DB.setFeature("http://xml.org/sax/features/external-parameter-entities", false)
      ...
      $DB.setFeature("http://xml.org/sax/features/external-general-entities", false)
  - pattern-not-inside: | # nosemgrep: slow-pattern-top-ellipsis
      ...
      $DB.setXIncludeAware(true)
      ...
      $DB.setNamespaceAware(true)
      ...
      $DB.setFeature("http://xml.org/sax/features/external-general-entities", false)
      ...
      $DB.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true)
      ...
      $DB.setFeature("http://xml.org/sax/features/external-parameter-entities", false)
  - pattern-not-inside: | # nosemgrep: slow-pattern-top-ellipsis
      ...
      $DB.setXIncludeAware(true)
      ...
      $DB.setNamespaceAware(true)
      ...
      $DB.setFeature("http://xml.org/sax/features/external-general-entities", false)
      ...
      $DB.setFeature("http://xml.org/sax/features/external-parameter-entities", false)
      ...
      $DB.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true)
  message: >-
    Document Builder being instantiated without calling the `setFeature` functions that are generally
    used for disabling entity processing.
    User controlled data in XML Document builder can result in XML Internal Entity Processing vulnerabilities
    like the disclosure of confidential data, denial of service, Server Side Request Forgery (SSRF), port
    scanning.
    Make sure to disable entity processing functionality.
  languages: [scala]
  severity: WARNING
  metadata:
    cwe:
    - 'CWE-611: Improper Restriction of XML External Entity Reference'
    owasp:
    - A04:2017 - XML External Entities (XXE)
    - A05:2021 - Security Misconfiguration
    source-rule-url: https://cheatsheetseries.owasp.org//cheatsheets/XML_External_Entity_Prevention_Cheat_Sheet.html
    category: security
    technology:
    - scala
    confidence: HIGH
    references:
    - https://owasp.org/Top10/A05_2021-Security_Misconfiguration
    cwe2022-top25: true
    cwe2021-top25: true
    subcategory:
    - vuln
    likelihood: LOW
    impact: MEDIUM