mcp-server-semgrep/semgrep-rules/python/lang/security/audit/dangerous-system-call-tainted-env-args.yaml

MCP Server for Semgrep Integration - static code analysis with AI

rules:
- id: dangerous-system-call-tainted-env-args
  mode: taint
  options:
    symbolic_propagation: true
  pattern-sources:
  - patterns:
    - pattern-either:
      - patterns:
        - pattern-either:
          - pattern: os.environ
          - pattern: os.environ.get('$FOO', ...)
          - pattern: os.environb
          - pattern: os.environb.get('$FOO', ...)
          - pattern: os.getenv('$ANYTHING', ...)
          - pattern: os.getenvb('$ANYTHING', ...)
      - patterns:
        - pattern-either:
          - patterns:
            - pattern-either:
              - pattern: sys.argv
              - pattern: sys.orig_argv
          - patterns:
            - pattern-inside: |
                $PARSER = argparse.ArgumentParser(...)
                ...
            - pattern-inside: |
                $ARGS = $PARSER.parse_args()
            - pattern: <... $ARGS ...>
          - patterns:
            - pattern-inside: |
                $PARSER = optparse.OptionParser(...)
                ...
            - pattern-inside: |
                $ARGS = $PARSER.parse_args()
            - pattern: <... $ARGS ...>
          - patterns:
            - pattern-either:
              - pattern-inside: |
                  $OPTS, $ARGS = getopt.getopt(...)
                  ...
              - pattern-inside: |
                  $OPTS, $ARGS = getopt.gnu_getopt(...)
                  ...
            - pattern-either:
              - patterns:
                - pattern-inside: |
                    for $O, $A in $OPTS:
                      ...
                - pattern: $A
              - pattern: $ARGS
  pattern-sinks:
  - patterns:
    - pattern-not: os.$W("...", ...)
    - pattern-either:
      - pattern: os.system(...)
      - pattern: |
          $X = __import__("os")
          ...
          $X.system(...)
      - pattern: |
          $X = __import__("os")
          ...
          getattr($X, "system")(...)
      - pattern: |
          $X = getattr(os, "system")
          ...
          $X(...)
      - pattern: |
          $X = __import__("os")
          ...
          $Y = getattr($X, "system")
          ...
          $Y(...)
      - pattern: os.popen(...)
      - pattern: os.popen2(...)
      - pattern: os.popen3(...)
      - pattern: os.popen4(...)
  message: >-
    Found user-controlled data used in a system call. This could allow a
    malicious actor to execute commands. Use the 'subprocess' module instead,
    which is easier to use without accidentally exposing a command injection
    vulnerability.
  metadata:
    source-rule-url: https://bandit.readthedocs.io/en/latest/plugins/b605_start_process_with_a_shell.html
    cwe:
    - "CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')"
    owasp:
    - A01:2017 - Injection
    - A03:2021 - Injection
    references:
    - https://semgrep.dev/docs/cheat-sheets/python-command-injection/
    asvs:
      section: 'V5: Validation, Sanitization and Encoding Verification Requirements'
      control_id: 5.2.4 Dyanmic Code Execution Features
      control_url: https://github.com/OWASP/ASVS/blob/master/4.0/en/0x13-V5-Validation-Sanitization-Encoding.md#v52-sanitization-and-sandboxing-requirements
      version: '4'
    category: security
    technology:
    - python
    confidence: MEDIUM
    cwe2022-top25: true
    cwe2021-top25: true
    subcategory:
    - vuln
    likelihood: MEDIUM
    impact: HIGH
  languages: [python]
  severity: ERROR