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

MCP Server for Semgrep Integration - static code analysis with AI

rules:
- id: dangerous-interactive-code-run-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-either:
      - pattern-inside: |
          $X = code.InteractiveConsole(...)
          ...
      - pattern-inside: |
          $X = code.InteractiveInterpreter(...)
          ...
    - pattern-either:
      - pattern-inside: |
          $X.push($PAYLOAD,...)
      - pattern-inside: |
          $X.runsource($PAYLOAD,...)
      - pattern-inside: |
          $X.runcode(code.compile_command($PAYLOAD),...)
      - pattern-inside: |
          $PL = code.compile_command($PAYLOAD,...)
          ...
          $X.runcode($PL,...)
    - pattern: $PAYLOAD
    - pattern-not: |
        $X.push("...",...)
    - pattern-not: |
        $X.runsource("...",...)
    - pattern-not: |
        $X.runcode(code.compile_command("..."),...)
    - pattern-not: |
        $PL = code.compile_command("...",...)
        ...
        $X.runcode($PL,...)
  message: >-
    Found user controlled data inside InteractiveConsole/InteractiveInterpreter method.
    This is dangerous if external data can reach this function call because it allows
    a malicious actor to run arbitrary Python code.
  metadata:
    cwe:
    - "CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')"
    owasp:
    - A03:2021 - Injection
    references:
    - https://semgrep.dev/docs/cheat-sheets/python-command-injection/
    category: security
    technology:
    - python
    confidence: MEDIUM
    subcategory:
    - vuln
    likelihood: MEDIUM
    impact: HIGH
  severity: WARNING
  languages:
  - python