mcp-server-semgrep/semgrep-rules/javascript/express/security/injection/raw-html-format.yaml

MCP Server for Semgrep Integration - static code analysis with AI

rules:
- id: raw-html-format
  message: >-
    User data flows into the host portion of this manually-constructed HTML.
    This can introduce a Cross-Site-Scripting (XSS) vulnerability if this comes from user-provided input.
    Consider using a sanitization library such as DOMPurify to sanitize the HTML within.
  metadata:
    cwe:
    - "CWE-79: Improper Neutralization of Input During Web Page Generation ('Cross-site Scripting')"
    owasp:
    - A07:2017 - Cross-Site Scripting (XSS)
    - A03:2021 - Injection
    references:
    - https://cheatsheetseries.owasp.org/cheatsheets/Cross_Site_Scripting_Prevention_Cheat_Sheet.html
    category: security
    technology:
    - express
    cwe2022-top25: true
    cwe2021-top25: true
    subcategory:
    - vuln
    likelihood: HIGH
    impact: MEDIUM
    confidence: MEDIUM
  languages:
  - javascript
  - typescript
  severity: WARNING
  mode: taint
  pattern-sources:
  - label: EXPRESS
    patterns:
    - pattern-either:
      - pattern-inside: function ... ($REQ, $RES) {...}
      - pattern-inside: function ... ($REQ, $RES, $NEXT) {...}
      - patterns:
        - pattern-either:
          - pattern-inside: $APP.$METHOD(..., function $FUNC($REQ, $RES) {...})
          - pattern-inside: $APP.$METHOD(..., function $FUNC($REQ, $RES, $NEXT) {...})
        - metavariable-regex:
            metavariable: $METHOD
            regex: ^(get|post|put|head|delete|options)$
    - pattern-either:
      - pattern: $REQ.query
      - pattern: $REQ.body
      - pattern: $REQ.params
      - pattern: $REQ.cookies
      - pattern: $REQ.headers
  - label: EXPRESSTS
    patterns:
    - pattern-either:
      - pattern-inside: |
          ({ $REQ }: Request,$RES: Response, $NEXT: NextFunction) =>
          {...}
      - pattern-inside: |
          ({ $REQ }: Request,$RES: Response) => {...}
    - focus-metavariable: $REQ
    - pattern-either:
      - pattern: params
      - pattern: query
      - pattern: cookies
      - pattern: headers
      - pattern: body
  - label: CLEAN
    by-side-effect: true
    patterns:
      - pattern-either:
          - pattern: $A($SOURCE)
          - pattern: $SANITIZE. ... .$A($SOURCE)
          - pattern: $A. ... .$SANITIZE($SOURCE)
      - focus-metavariable: $SOURCE
      - metavariable-regex:
          metavariable: $A
          regex: (?i)(.*valid|.*sanitiz)
  pattern-sinks:
  - requires: (EXPRESS and not CLEAN) or (EXPRESSTS and not CLEAN)
    patterns:
    - pattern-either:
      - patterns:
        - pattern-either:
          - pattern: '"$HTMLSTR" + $EXPR'
          - pattern: '"$HTMLSTR".concat(...)'
          - pattern: util.format($HTMLSTR, ...)
        - metavariable-pattern:
            metavariable: $HTMLSTR
            language: generic
            pattern: <$TAG ...
      - patterns:
        - pattern: |
            `...`
        - pattern-regex: |
            .*<\w+.*