diff --git a/DEVELOPMENT.md b/DEVELOPMENT.md index df88b8f..b5ba7cb 100644 --- a/DEVELOPMENT.md +++ b/DEVELOPMENT.md @@ -376,14 +376,23 @@ Puppet and Salt also run `cm.resolve_catalog_conflicts()` after renderer role co capture_file(abs_path, role_name, reason, policy, path_filter, ...) -> skip if already seen globally or in this role -> skip if --exclude-path matches - -> ask IgnorePolicy.deny_reason(abs_path) - -> stat owner/group/mode with fsutil.stat_triplet() - -> copy to artifacts// + -> ask IgnorePolicy.inspect_file(abs_path) + -> open the source through fsutil.open_no_follow_path() + -> reject symlinks in any path component, not only the leaf + -> fstat() the opened descriptor + -> reject non-regular or over-size files + -> read the exact bytes from that descriptor + -> scan those bytes for binary/secret content unless dangerous + -> use the inspected fstat() for owner/group/mode metadata + -> write the inspected bytes to artifacts// + with no-follow destination creation -> append ManagedFile -> mark seen in role/global ``` -`fsutil.stat_triplet()` returns owner, group, and a zero-padded octal mode string. It falls back to numeric uid/gid strings if user/group names cannot be resolved. +This ordering is intentional. Enroll should not scan one file and later copy a different file after a race. When `IgnorePolicy.inspect_file()` succeeds, `capture_file()` writes the exact bytes that were inspected and uses the same descriptor's stat metadata. + +`fsutil.stat_triplet()` and `stat_triplet_from_stat()` return owner, group, and a zero-padded octal mode string. They fall back to numeric uid/gid strings if user/group names cannot be resolved. ### 7.2 `capture_link()` @@ -450,6 +459,20 @@ regex:^/path/...$ regex `expand_includes()` is conservative: it ignores symlinks, respects excludes, caps file counts, and returns notes for unmatched patterns or caps. +### 7.6 Output, artifact, and cache safety helpers + +Several safety helpers protect privileged runs from following attacker-controlled paths: + +- `fsutil.open_no_follow_path()` opens source and artifact paths component-by-component, rejecting symlinked parent directories as well as symlinked leaf files. +- `harvest_safety.prepare_new_private_dir()` is used for user-facing plaintext output directories such as `harvest --out` and default manifest output; it refuses existing final paths and creates `0700` directories. +- `harvest_safety.ensure_safe_output_parent()` is used when writing output files such as reports or encrypted SOPS bundles. It validates parents before staging a temporary file and atomically replacing the final path. +- `harvest_safety.ensure_private_dir()` is used for persistent internal directories such as Enroll's cache root. Existing directories are allowed, but symlink components and unsafe root-run parents are refused. +- `cache.new_harvest_cache_dir()` creates unpredictable per-harvest cache directories beneath the hardened cache root with `mkdtemp()` and private permissions. +- `manifest_safety.safe_artifact_file()` validates referenced harvested artifacts before renderers copy them. It rejects absolute or `..` paths, symlinks, non-regular files, hardlinks, and paths that resolve outside the artifact root. +- `manifest_safety.prepare_manifest_output_dir()` refuses unsafe manifest output paths. In `--fqdn` site mode, where an existing tree is intentionally reused, it walks the existing output tree and refuses symlinks before merging generated files. + +When adding a new code path that writes plaintext host state, prefer these helpers over raw `mkdir(parents=True)`, `open()`, `shutil.copy*()`, or `tar.extract*()`. + --- ## 8. Platform and package backends @@ -788,8 +811,7 @@ SOPS mode: The renderers do not know about SOPS. -Note: Manifest deliberately hooks into validate() to make sure the harvest meets the schema and -doesn't contain dangerous tamperings before turning it into config management code. +Before dispatching to a renderer, `manifest.manifest()` calls `validate.validate_harvest()` with normal schema validation enabled. That means generated configuration-management code is only rendered after Enroll has checked the bundle schema, referenced artifact existence, and artifact safety. If validation fails, manifest generation stops rather than trying to produce best-effort output from a malformed or tampered bundle. --- @@ -1380,17 +1402,24 @@ This is intended to answer “what did Enroll collect and why?” 1. `state.json` exists, 2. it parses as JSON, 3. it validates against the vendored schema unless `--no-schema` is set, -4. every `managed_file.src_rel` points to an artifact file, -5. firewall runtime generated artifacts exist, -6. there are no unreferenced artifact files, reported as warnings. -7. there are no malicious or unsafe bits such as symlinks/hardlinks etc traversing out of the artifact tree +4. every `managed_file.src_rel` is relative and points to a safe artifact file, +5. firewall runtime generated artifacts exist and are safe, +6. the top-level `artifacts/` path is a real directory rather than a symlink or file, +7. the whole artifact tree contains no symlink directories, symlink files, hardlinks, special files, or paths that escape the artifact root, +8. unreferenced artifact files are reported as warnings. + +`validate_harvest()` is used in three important contexts: + +- `enroll validate` exposes the checks directly to users. +- `manifest.manifest()` validates before rendering Ansible/Puppet/Salt output. +- `diff.compare_harvests()` validates both input bundles before comparing them, using `no_schema=True` so older harvests can still be inspected while artifact safety checks remain active. + +`diff --enforce` renders the old harvest through `manifest.manifest()`, so enforcement also passes through manifest-time validation before a local apply tool is invoked. It returns a `ValidationResult` with `errors`, `warnings`, `ok()`, `to_dict()`, and `to_text()`. The CLI supports local schema override with `--schema`, warning failure with `--fail-on-warnings`, JSON/text output, and `--out`. -Note that manifest() hooks into validate() to make sure the harvest is safe before rendering it into config management code. - --- ## 19. Remote harvesting @@ -1457,7 +1486,7 @@ Unknown host keys are rejected by default through Paramiko's reject policy. User - device nodes, - anything resolving outside the destination. -This helper is reused by remote harvest, manifest SOPS extraction, and diff bundle resolution. +This helper is reused by remote harvest, manifest SOPS extraction, validate/diff bundle resolution, and any code path that needs to unpack a harvest tarball. Do not use raw `tar.extractall()` for user- or remote-provided bundles. --- diff --git a/enroll/cache.py b/enroll/cache.py index 1dc656b..3a53b87 100644 --- a/enroll/cache.py +++ b/enroll/cache.py @@ -8,6 +8,8 @@ from datetime import datetime from pathlib import Path from typing import Optional +from .harvest_safety import OutputSafetyError, ensure_private_dir + def _safe_component(s: str) -> str: s = s.strip() @@ -44,16 +46,17 @@ class HarvestCache: def _ensure_dir_secure(path: Path) -> None: - """Create a directory with restrictive permissions; refuse symlinks.""" - # Refuse a symlink at the leaf. - if path.exists() and path.is_symlink(): - raise RuntimeError(f"Refusing to use symlink path: {path}") - path.mkdir(parents=True, exist_ok=True, mode=0o700) + """Create a private cache directory with output-path safety checks. + + Cache roots are persistent, so existing directories are allowed, but they + still need the same symlink-component and root-parent trust checks as + plaintext harvest/manifest output paths. + """ + try: - os.chmod(path, 0o700) - except OSError: - # Best-effort; on some FS types chmod may fail. - pass + ensure_private_dir(path, label="cache directory") + except OutputSafetyError as e: + raise RuntimeError(str(e)) from e def new_harvest_cache_dir(*, hint: Optional[str] = None) -> HarvestCache: diff --git a/enroll/harvest_safety.py b/enroll/harvest_safety.py index b6e4bc4..d6d738c 100644 --- a/enroll/harvest_safety.py +++ b/enroll/harvest_safety.py @@ -69,6 +69,8 @@ def _assert_existing_output_dir_component(path: Path, *, label: str) -> None: raise OutputSafetyError( f"{label} parent path contains a symlink; refusing: {path}" ) + if not stat.S_ISDIR(st.st_mode): + raise OutputSafetyError(f"{label} parent is not a directory: {path}") _assert_trusted_root_parent(path, st, label=label) @@ -214,6 +216,24 @@ def write_text_output_file( return out +def ensure_private_dir(path: str | Path, *, label: str = "output") -> Path: + """Create or validate a private directory without requiring it to be empty. + + This is for persistent internal directories such as Enroll's cache root, + where existing contents are expected across runs. It uses the same + component-by-component symlink and root-parent trust checks as user-facing + plaintext output directories, but permits an existing final directory. + """ + + out = Path(path).expanduser() + sentinel = out / ".enroll-private-dir-check" + _assert_no_existing_symlink_components(sentinel, label=label) + out = _mkdir_private_dir_tree(out, label=label, final_must_be_new=False) + _assert_no_existing_symlink_components(sentinel, label=label) + _chmod_private(out) + return out + + def prepare_new_private_dir(path: str | Path, *, label: str = "output") -> Path: """Create a brand-new private output directory. diff --git a/enroll/validate.py b/enroll/validate.py index 60d7f7c..e8c65ea 100644 --- a/enroll/validate.py +++ b/enroll/validate.py @@ -232,65 +232,79 @@ def validate_harvest( # Validate the whole artifact tree too, so unreferenced symlinks, # hardlinks, special files, and path-shaping tricks do not survive # validation simply because no managed_file currently references them. - if artifacts_dir.exists() and artifacts_dir.is_dir(): - for root, dirs, files in os.walk(artifacts_dir, followlinks=False): - root_p = Path(root) - for name in list(dirs): - fp = root_p / name - try: - st = fp.lstat() - except FileNotFoundError: - continue - if stat.S_ISLNK(st.st_mode): - errors.append(f"artifact directory is a symlink: {fp}") - elif not stat.S_ISDIR(st.st_mode): - errors.append(f"artifact directory is not a directory: {fp}") + if artifacts_dir.exists(): + try: + artifacts_st = artifacts_dir.lstat() + except OSError as e: + errors.append(f"unable to inspect artifacts directory: {e}") + else: + if stat.S_ISLNK(artifacts_st.st_mode): + errors.append(f"artifacts directory is a symlink: {artifacts_dir}") + elif not stat.S_ISDIR(artifacts_st.st_mode): + errors.append(f"artifacts path is not a directory: {artifacts_dir}") + else: + for root, dirs, files in os.walk(artifacts_dir, followlinks=False): + root_p = Path(root) + for name in list(dirs): + fp = root_p / name + try: + st = fp.lstat() + except FileNotFoundError: + continue + if stat.S_ISLNK(st.st_mode): + errors.append(f"artifact directory is a symlink: {fp}") + elif not stat.S_ISDIR(st.st_mode): + errors.append( + f"artifact directory is not a directory: {fp}" + ) - for name in files: - fp = root_p / name - try: - st = fp.lstat() - except FileNotFoundError: - continue - try: - rel = fp.relative_to(artifacts_dir) - except ValueError: - errors.append(f"artifact escapes artifact root: {fp}") - continue - parts = rel.parts - if len(parts) < 2: - errors.append(f"artifact is not under a role directory: {fp}") - continue - role_name = parts[0] - src_rel = "/".join(parts[1:]) + for name in files: + fp = root_p / name + try: + st = fp.lstat() + except FileNotFoundError: + continue + try: + rel = fp.relative_to(artifacts_dir) + except ValueError: + errors.append(f"artifact escapes artifact root: {fp}") + continue + parts = rel.parts + if len(parts) < 2: + errors.append( + f"artifact is not under a role directory: {fp}" + ) + continue + role_name = parts[0] + src_rel = "/".join(parts[1:]) - if stat.S_ISLNK(st.st_mode): - errors.append( - f"artifact is a symlink: artifacts/{role_name}/{src_rel}" - ) - continue - if not stat.S_ISREG(st.st_mode): - errors.append( - f"artifact is not a regular file: artifacts/{role_name}/{src_rel}" - ) - continue - if st.st_nlink > 1: - errors.append( - f"artifact is hardlinked: artifacts/{role_name}/{src_rel}" - ) - continue - try: - safe_artifact_file(bundle.dir, role_name, src_rel) - except (FileNotFoundError, ArtifactSafetyError) as e: - errors.append( - f"unsafe artifact: artifacts/{role_name}/{src_rel}: {e}" - ) - continue + if stat.S_ISLNK(st.st_mode): + errors.append( + f"artifact is a symlink: artifacts/{role_name}/{src_rel}" + ) + continue + if not stat.S_ISREG(st.st_mode): + errors.append( + f"artifact is not a regular file: artifacts/{role_name}/{src_rel}" + ) + continue + if st.st_nlink > 1: + errors.append( + f"artifact is hardlinked: artifacts/{role_name}/{src_rel}" + ) + continue + try: + safe_artifact_file(bundle.dir, role_name, src_rel) + except (FileNotFoundError, ArtifactSafetyError) as e: + errors.append( + f"unsafe artifact: artifacts/{role_name}/{src_rel}: {e}" + ) + continue - if (role_name, src_rel) not in referenced: - warnings.append( - f"unreferenced artifact present: artifacts/{role_name}/{src_rel}" - ) + if (role_name, src_rel) not in referenced: + warnings.append( + f"unreferenced artifact present: artifacts/{role_name}/{src_rel}" + ) return ValidationResult(errors=errors, warnings=warnings) finally: diff --git a/tests/test_cache_security.py b/tests/test_cache_security.py index 4fda1e1..a1b7622 100644 --- a/tests/test_cache_security.py +++ b/tests/test_cache_security.py @@ -95,3 +95,44 @@ def test_enroll_cache_dir_uses_default_when_xdg_not_set(monkeypatch): monkeypatch.delenv("XDG_CACHE_HOME", raising=False) result = enroll_cache_dir() assert str(result).endswith("/.local/cache/enroll") + + +def test_ensure_dir_secure_refuses_symlink_parent(tmp_path: Path): + from enroll.cache import _ensure_dir_secure + + target = tmp_path / "target" + target.mkdir() + link = tmp_path / "link" + link.symlink_to(target, target_is_directory=True) + + with pytest.raises(RuntimeError, match="symlink"): + _ensure_dir_secure(link / "enroll" / "harvest") + + assert not (target / "enroll" / "harvest").exists() + + +def test_ensure_dir_secure_rejects_unsafe_root_parent(tmp_path: Path, monkeypatch): + from enroll.cache import _ensure_dir_secure + import enroll.harvest_safety as hs + + untrusted = tmp_path / "untrusted" + untrusted.mkdir() + untrusted.chmod(0o777) + + monkeypatch.setattr(hs, "_effective_uid", lambda: 0) + with pytest.raises(RuntimeError, match="not owned by root|writable by group/other"): + _ensure_dir_secure(untrusted / "cache") + + +def test_ensure_dir_secure_rejects_existing_file_when_not_root( + tmp_path: Path, monkeypatch +): + from enroll.cache import _ensure_dir_secure + import enroll.harvest_safety as hs + + path = tmp_path / "cache" + path.write_text("not a dir", encoding="utf-8") + + monkeypatch.setattr(hs, "_effective_uid", lambda: 1000) + with pytest.raises(RuntimeError, match="not a directory"): + _ensure_dir_secure(path) diff --git a/tests/test_validate.py b/tests/test_validate.py index 5ac33c9..002d2cf 100644 --- a/tests/test_validate.py +++ b/tests/test_validate.py @@ -453,3 +453,35 @@ def test_validate_harvest_rejects_unreferenced_artifact_symlink(tmp_path: Path): assert result.ok is False assert any("symlink" in e for e in result.errors) + + +def test_validate_harvest_rejects_top_level_artifacts_symlink(tmp_path: Path): + bundle_dir = tmp_path / "bundle" + bundle_dir.mkdir() + target = tmp_path / "artifact-target" + target.mkdir() + (bundle_dir / "artifacts").symlink_to(target, target_is_directory=True) + (bundle_dir / "state.json").write_text( + json.dumps({"roles": {"users": {"managed_files": []}}}), + encoding="utf-8", + ) + + result = validate_harvest(str(bundle_dir), no_schema=True) + + assert result.ok is False + assert any("artifacts directory is a symlink" in e for e in result.errors) + + +def test_validate_harvest_rejects_top_level_artifacts_file(tmp_path: Path): + bundle_dir = tmp_path / "bundle" + bundle_dir.mkdir() + (bundle_dir / "artifacts").write_text("not a directory", encoding="utf-8") + (bundle_dir / "state.json").write_text( + json.dumps({"roles": {"users": {"managed_files": []}}}), + encoding="utf-8", + ) + + result = validate_harvest(str(bundle_dir), no_schema=True) + + assert result.ok is False + assert any("artifacts path is not a directory" in e for e in result.errors)