molecule-ci/.github/workflows/validate-workspace-template.yml

name: Validate Workspace Template
on:
  workflow_call:

# Defense-in-depth on the GITHUB_TOKEN scope. This workflow runs
# untrusted-by-design code from the calling template repo — pip
# installs the template's requirements.txt (post-install hooks),
# imports adapter.py, and `docker build`s the Dockerfile (RUN
# steps). Each of those primitives can execute arbitrary code with
# the token in env. Pinning `contents: read` means the worst a
# malicious template PR can do with the token is read public repo
# state — no write to issues, no push to branches, no comment-spam,
# no workflow re-trigger.
#
# Fork-PR lockdown (#135): the workflow splits into two jobs:
#
#   validate-static  — file-content checks only (secret scan, YAML
#                      parse, AST inspection of adapter.py without
#                      import). Always runs, including external fork
#                      PRs. Safe because no third-party code executes.
#
#   validate-runtime — pip install requirements.txt + import
#                      adapter.py + docker build. SKIPPED on fork
#                      PRs because each step is arbitrary code
#                      execution from the template repo's perspective.
#                      Internal PRs and post-merge runs still get
#                      the full coverage.
#
# What this prevents: a malicious external PR can no longer
# crypto-mine on the runner, DNS-exfiltrate runner metadata, or
# attempt to read GitHub-Actions internal env via a setup.py
# postinstall hook. They still get static feedback (secret scan
# is the most important security check anyway).
#
# What this does NOT prevent: malicious template metadata that
# passes static checks. The runtime job catches those once the PR
# merges (or an internal contributor reposts the change), at which
# point branch protection on staging/main blocks the merge if
# runtime validation fails.
permissions:
  contents: read

jobs:
  validate-static:
    name: Template validation (static)
    runs-on: ubuntu-latest
    timeout-minutes: 5
    steps:
      # Calling template repo (Dockerfile + config.yaml + adapter.py).
      - uses: actions/checkout@v4
      # Canonical validator script lives in molecule-ci, fetched fresh on
      # every run. The previous setup expected `.molecule-ci/scripts/` to
      # be vendored INTO each template repo, which drifted across the 8
      # template repos as the validator evolved. Single source of truth
      # eliminates that drift class entirely — every template runs the
      # same canonical contract check on every CI run.
      - uses: actions/checkout@v4
        with:
          repository: Molecule-AI/molecule-ci
          path: .molecule-ci-canonical
      - uses: actions/setup-python@v5
        with:
          python-version: "3.11"
      # Secret scan — the most important check. Always runs.
      - name: Check for secrets
        run: |
          python3 - << 'PYEOF'
          import os, re, sys
          from pathlib import Path

          PATTERNS = [
              re.compile(r'''["']sk-ant-[a-zA-Z0-9]{50,}["']'''),
              re.compile(r'''["']ghp_[a-zA-Z0-9]{36,}["']'''),
              re.compile(r'''["']AKIA[A-Z0-9]{16}["']'''),
              re.compile(r'''["'][a-zA-Z0-9/+=]{40}["']'''),
              re.compile(r'''["']sk_test_[a-zA-Z0-9]{24,}["']'''),
              re.compile(r'''["']Bearer\s+[a-zA-Z0-9_.-]{20,}["']'''),
              re.compile(r'''ghp_[a-zA-Z0-9]{36,}'''),
              re.compile(r'''sk-ant-[a-zA-Z0-9]{50,}'''),
          ]
          SKIP_DIRS = {'.molecule-ci', '.git', 'node_modules', '__pycache__'}
          EXTENSIONS = {'.yaml', '.yml', '.md', '.py', '.sh'}

          def is_false_positive(line):
              ctx = line.lower()
              return '...' in ctx or '<example' in ctx or '</example' in ctx

          root = Path(os.environ.get('GITHUB_WORKSPACE', '.'))
          warnings = []
          for dirpath, dirnames, filenames in os.walk(root):
              dirnames[:] = [d for d in dirnames if d not in SKIP_DIRS]
              for filename in filenames:
                  if Path(filename).suffix not in EXTENSIONS:
                      continue
                  filepath = Path(dirpath) / filename
                  try:
                      with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
                          for lineno, line in enumerate(f.readlines(), 1):
                              for pattern in PATTERNS:
                                  for match in pattern.finditer(line):
                                      if not is_false_positive(line):
                                          warnings.append(f"  {filepath}:{lineno}: {match.group(0)[:40]}...")
                  except Exception:
                      pass

          if warnings:
              print("::error::Potential secret found in committed files:")
              for w in warnings:
                  print(w)
              sys.exit(1)
          else:
              print("::notice::No secrets detected")
          PYEOF          
      # Static-only validator — file existence checks, YAML parse,
      # AST inspection of adapter.py (no import). Doesn't execute
      # any third-party code; safe on fork PRs.
      - run: pip install pyyaml -q
      - run: python3 .molecule-ci-canonical/scripts/validate-workspace-template.py --static-only

  validate-runtime:
    name: Template validation (runtime)
    runs-on: ubuntu-latest
    timeout-minutes: 15
    needs: validate-static
    # Skip when the PR comes from a fork — those are external,
    # untrusted, and would let attackers run pip install / docker
    # build / adapter.py import on our runner. Internal PRs (head
    # repo == base repo, fork == false) and push events to internal
    # branches both keep full coverage.
    #
    # github.event.pull_request.head.repo.fork is null for non-PR
    # events (push, schedule, etc.) — defaults to running.
    if: github.event.pull_request.head.repo.fork != true
    steps:
      - uses: actions/checkout@v4
      - uses: actions/checkout@v4
        with:
          repository: Molecule-AI/molecule-ci
          path: .molecule-ci-canonical
      - uses: actions/setup-python@v5
        with:
          python-version: "3.11"
          # Cache pip against the calling repo's own requirements.txt
          # (the file we install one step below). Pointing the cache key
          # at the validator's own deps was decorative — pyyaml never
          # changes, so the key never invalidated even when the template
          # added a heavy dep like crewai.
          cache: "pip"
          cache-dependency-path: requirements.txt
      - run: pip install pyyaml -q
      # Install the template's runtime dependencies so the validator's
      # `check_adapter_runtime_load()` can import adapter.py the same way
      # the workspace container does at boot. Without this, a
      # syntactically-valid adapter that ImportErrors on a missing
      # transitive dep would build clean and crash on first user prompt.
      # The fallback (no requirements.txt) installs the runtime alone so
      # BaseAdapter is at least importable for the class-discovery check.
      - if: hashFiles('requirements.txt') != ''
        run: pip install -q -r requirements.txt
      - if: hashFiles('requirements.txt') == ''
        run: pip install -q molecule-ai-workspace-runtime
      # Full validator — includes adapter.py import (exec_module).
      - run: python3 .molecule-ci-canonical/scripts/validate-workspace-template.py
      - name: Docker build smoke test
        if: hashFiles('Dockerfile') != ''
        run: docker build -t template-test . --no-cache 2>&1 | tail -5 && echo "✓ Docker build succeeded"