# pip
python3 -m pip install semgrep

# Homebrew
brew install semgrep

# Docker
docker run --rm -v "${PWD}:/src" returntocorp/semgrep semgrep --config auto /src

# Update
pip install --upgrade semgrep

semgrep --config auto .                    # Auto-detect rules
semgrep --config auto --metrics=off .      # Disable telemetry for proprietary code

semgrep --config p/<RULESET> .             # Single ruleset
semgrep --config p/security-audit --config p/trailofbits .  # Multiple

semgrep --config p/security-audit --sarif -o results.sarif .   # SARIF
semgrep --config p/security-audit --json -o results.json .     # JSON
semgrep --config p/security-audit --dataflow-traces .          # Show data flow

semgrep --config p/python app.py           # Single file
semgrep --config p/javascript src/         # Directory
semgrep --config auto --include='**/test/**' .  # Include tests (excluded by default)

rules:
  - id: hardcoded-password
    languages: [python]
    message: "Hardcoded password detected: $PASSWORD"
    severity: ERROR
    pattern: password = "$PASSWORD"

rules:
  - id: sql-injection
    languages: [python]
    message: "Potential SQL injection"
    severity: ERROR
    patterns:
      - pattern-either:
          - pattern: cursor.execute($QUERY)
          - pattern: db.execute($QUERY)
      - pattern-not:
          - pattern: cursor.execute("...", (...))
      - metavariable-regex:
          metavariable: $QUERY
          regex: .*\+.*|.*\.format\(.*|.*%.*

# Pattern `os.system($CMD)` catches this:
os.system(user_input)  # Found

# Same pattern misses this:
cmd = user_input
processed = cmd.strip()
os.system(processed)  # Missed - no direct match

rules:
  - id: command-injection
    languages: [python]
    message: "User input flows to command execution"
    severity: ERROR
    mode: taint
    pattern-sources:
      - pattern: request.args.get(...)
      - pattern: request.form[...]
      - pattern: request.json
    pattern-sinks:
      - pattern: os.system($SINK)
      - pattern: subprocess.call($SINK, shell=True)
      - pattern: subprocess.run($SINK, shell=True, ...)
    pattern-sanitizers:
      - pattern: shlex.quote(...)
      - pattern: int(...)

rules:
  - id: flask-sql-injection
    languages: [python]
    message: "SQL injection: user input flows to query without parameterization"
    severity: ERROR
    metadata:
      cwe: "CWE-89: SQL Injection"
      owasp: "A03:2021 - Injection"
      confidence: HIGH
    mode: taint
    pattern-sources:
      - pattern: request.args.get(...)
      - pattern: request.form[...]
      - pattern: request.json
    pattern-sinks:
      - pattern: cursor.execute($QUERY)
      - pattern: db.execute($QUERY)
    pattern-sanitizers:
      - pattern: int(...)
    fix: cursor.execute($QUERY, (params,))

# test_rule.py
def test_vulnerable():
    user_input = request.args.get("id")
    # ruleid: flask-sql-injection
    cursor.execute("SELECT * FROM users WHERE id = " + user_input)

def test_safe():
    user_input = request.args.get("id")
    # ok: flask-sql-injection
    cursor.execute("SELECT * FROM users WHERE id = ?", (user_input,))

semgrep --test rules/

name: Semgrep

on:
  push:
    branches: [main]
  pull_request:
  schedule:
    - cron: '0 0 1 * *'  # Monthly

jobs:
  semgrep:
    runs-on: ubuntu-latest
    container:
      image: returntocorp/semgrep

    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0  # Required for diff-aware scanning

      - name: Run Semgrep
        run: |
          if [ "${{ github.event_name }}" = "pull_request" ]; then
            semgrep ci --baseline-commit ${{ github.event.pull_request.base.sha }}
          else
            semgrep ci
          fi
        env:
          SEMGREP_RULES: >-
            p/security-audit
            p/owasp-top-ten
            p/trailofbits

tests/fixtures/
**/testdata/
generated/
vendor/
node_modules/

password = get_from_vault()  # nosemgrep: hardcoded-password
dangerous_but_safe()  # nosemgrep

semgrep --config rules/ --time .    # Check rule performance
ulimit -n 4096                       # Increase file descriptors for large codebases

rules:
  - id: my-rule
    paths:
      include: [src/]
      exclude: [src/generated/]

pip install semgrep-rules-manager
semgrep-rules-manager --dir ~/semgrep-rules download
semgrep -f ~/semgrep-rules .