test(safety): allow public GitHub attachments

This commit is contained in:
Jason Morcos
2026-08-02 16:31:15 -07:00
parent 2c93cb3097
commit fc6240b72e
4 changed files with 217 additions and 43 deletions
+64 -35
View File
@@ -9,23 +9,37 @@ from smartthings_local.ocf.state_cache import StateCache
from smartthings_local.protocol.dtls_session import DtlsCoapSession
def _parameter_names(callable_object) -> list[str]:
return list(inspect.signature(callable_object).parameters)
def _assert_compatible_signature(callable_object, expected: list[str]) -> None:
"""Require the existing call surface while allowing safe extensions."""
parameters = list(inspect.signature(callable_object).parameters.values())
assert [parameter.name for parameter in parameters[: len(expected)]] == expected
for parameter in parameters[len(expected) :]:
assert (
parameter.kind
in (
inspect.Parameter.VAR_POSITIONAL,
inspect.Parameter.VAR_KEYWORD,
)
or parameter.default is not inspect.Parameter.empty
)
def test_dtls_session_constructor_keeps_file_memory_and_local_port_inputs():
assert _parameter_names(DtlsCoapSession) == [
"host",
"port",
"cert_path",
"key_path",
"cert_pem",
"key_pem",
"on_notification",
"mtu",
"rate_limit_rps",
"local_port",
]
_assert_compatible_signature(
DtlsCoapSession,
[
"host",
"port",
"cert_path",
"key_path",
"cert_pem",
"key_pem",
"on_notification",
"mtu",
"rate_limit_rps",
"local_port",
],
)
def test_dtls_session_keeps_current_consumer_methods():
@@ -42,23 +56,32 @@ def test_dtls_session_keeps_current_consumer_methods():
"subscribe",
}
assert expected <= set(dir(DtlsCoapSession))
assert _parameter_names(DtlsCoapSession.get) == [
"self",
"path_segs",
"query",
"timeout",
]
assert _parameter_names(DtlsCoapSession.post) == [
"self",
"path_segs",
"body_cbor",
"timeout",
]
assert _parameter_names(DtlsCoapSession.subscribe) == ["self", "path_segs"]
_assert_compatible_signature(
DtlsCoapSession.get,
[
"self",
"path_segs",
"query",
"timeout",
],
)
_assert_compatible_signature(
DtlsCoapSession.post,
[
"self",
"path_segs",
"body_cbor",
"timeout",
],
)
_assert_compatible_signature(
DtlsCoapSession.subscribe,
["self", "path_segs"],
)
def test_state_cache_keeps_current_consumer_surface():
assert _parameter_names(StateCache) == ["descriptor"]
_assert_compatible_signature(StateCache, ["descriptor"])
expected = {
"apply_optimistic",
"apply_rep",
@@ -73,10 +96,16 @@ def test_state_cache_keeps_current_consumer_surface():
def test_observe_refresh_task_keeps_current_consumer_surface():
assert _parameter_names(ObserveRefreshTask) == [
"session",
"paths",
"interval_s",
"logger",
]
assert _parameter_names(ObserveRefreshTask.run_forever) == ["self", "stop"]
_assert_compatible_signature(
ObserveRefreshTask,
[
"session",
"paths",
"interval_s",
"logger",
],
)
_assert_compatible_signature(
ObserveRefreshTask.run_forever,
["self", "stop"],
)
+62
View File
@@ -13,6 +13,22 @@ def test_documentation_addresses_and_synthetic_uuid_are_safe():
assert check_share_safety.scan_text("fixture.txt", text) == []
def test_dotted_object_identifiers_are_not_ipv4_addresses():
text = "extendedKeyUsage = 1.3.6.1.4.1.51414.0.1.2"
assert check_share_safety.scan_text("fixture.txt", text) == []
def test_public_github_attachment_uuid_is_safe_but_bare_uuid_is_not():
value = "cc1dca15-f272-4625-" + "a13c-2dc82283ff95"
public_url = f"https://github.com/user-attachments/assets/{value}"
assert check_share_safety.scan_text("README.md", public_url) == []
assert check_share_safety.scan_text("fixture.txt", value) == [
check_share_safety.Finding("fixture.txt", 1, "UUID")
]
def test_findings_never_echo_matched_content():
cases = {
"PEM_PRIVATE_KEY": "-----BEGIN " + "PRIVATE KEY-----",
@@ -94,3 +110,49 @@ def test_changed_paths_include_staged_unstaged_and_untracked_files(
"staged.txt",
"untracked.txt",
]
def test_committed_scan_ignores_unchanged_findings_but_checks_added_lines(
tmp_path, monkeypatch
):
def git(*args):
return subprocess.run(
[
"git",
"-c",
"commit.gpgsign=false",
"-c",
"user.name=Test",
"-c",
"user.email=" + "test" + chr(64) + "example.invalid",
*args,
],
cwd=tmp_path,
capture_output=True,
check=True,
text=True,
)
candidate = tmp_path / "candidate.txt"
private_one = "10." + "24.8.9"
private_two = "10." + "24.8.10"
git("init", "--quiet")
candidate.write_text(f"existing {private_one}\n")
git("add", "candidate.txt")
git("commit", "--quiet", "-m", "baseline")
base = git("rev-parse", "HEAD").stdout.strip()
candidate.write_text(f"existing {private_one}\nsafe addition\n")
git("add", "candidate.txt")
git("commit", "--quiet", "-m", "safe change")
monkeypatch.chdir(tmp_path)
assert check_share_safety.check_changed(base) == []
candidate.write_text(
f"existing {private_one}\nsafe addition\nintroduced {private_two}\n"
)
git("add", "candidate.txt")
git("commit", "--quiet", "-m", "unsafe change")
assert check_share_safety.check_changed(base) == [
check_share_safety.Finding("candidate.txt", 3, "NON_DOCUMENTATION_IPV4")
]
+6 -2
View File
@@ -9,6 +9,8 @@ from smartthings_local.ocf.observe_refresh import ObserveRefreshTask
from smartthings_local.ocf.poll_scheduler import PollScheduler, PollTier
from smartthings_local.ocf.state_cache import StateCache
_THREAD_DEADLINE_S = 2.0
class _Session:
def ping(self):
@@ -45,9 +47,11 @@ def _assert_worker_stops(target, name: str):
worker = threading.Thread(target=run, name=name, daemon=True)
worker.start()
assert stop.waiting.wait(0.5), f"{name} did not enter an interruptible wait"
assert stop.waiting.wait(_THREAD_DEADLINE_S), (
f"{name} did not enter an interruptible wait"
)
stop.set()
worker.join(0.5)
worker.join(_THREAD_DEADLINE_S)
assert not worker.is_alive(), f"{name} did not stop"
assert errors == [], f"{name} raised {errors[0]}"
+85 -6
View File
@@ -1,5 +1,5 @@
#!/usr/bin/env python3
"""Check changed public files for common private-data and secret shapes.
"""Check introduced public content for common private-data and secret shapes.
Findings contain only path, line, and rule ID. Matched content is never
printed because it may itself be sensitive.
@@ -92,11 +92,14 @@ PATTERNS = (
re.compile(r"(?i)\b(?:qr[_-]?payload|setup[_-]?payload)\b\s*(?::|=)"),
),
)
UUID_RE = re.compile(
r"(?i)(?<![0-9a-f])[0-9a-f]{8}-[0-9a-f]{4}-[1-5][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}(?![0-9a-f])"
UUID_PATTERN = r"(?<![0-9a-f])[0-9a-f]{8}-[0-9a-f]{4}-[1-5][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}(?![0-9a-f])"
UUID_RE = re.compile(UUID_PATTERN, re.IGNORECASE)
PUBLIC_GITHUB_ATTACHMENT_RE = re.compile(
rf"https://github\.com/user-attachments/assets/(?P<uuid>{UUID_PATTERN})",
re.IGNORECASE,
)
IPV4_RE = re.compile(
r"(?<![0-9])(?:25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(?:\.(?:25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}(?![0-9])"
r"(?<![0-9.])(?:25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(?:\.(?:25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}(?![0-9.])"
)
IPV6_RE = re.compile(
r"(?i)(?<![0-9a-f:])(?:\[)?(?:[0-9a-f]{0,4}:){2,7}[0-9a-f]{0,4}(?:%[A-Za-z0-9_.-]+)?(?:\])?(?![0-9a-f:])"
@@ -132,11 +135,16 @@ def _safe_ipv6(value: str) -> bool:
def scan_text(path: str, text: str) -> list[Finding]:
findings: set[Finding] = set()
for line_number, line in enumerate(text.splitlines(), start=1):
public_attachment_uuids = {
match.group("uuid").lower()
for match in PUBLIC_GITHUB_ATTACHMENT_RE.finditer(line)
}
for rule_id, pattern in PATTERNS:
if pattern.search(line):
findings.add(Finding(path, line_number, rule_id))
for match in UUID_RE.finditer(line):
if match.group(0).lower() not in SAFE_UUIDS:
value = match.group(0).lower()
if value not in SAFE_UUIDS and value not in public_attachment_uuids:
findings.add(Finding(path, line_number, "UUID"))
for match in IPV4_RE.finditer(line):
if not _safe_ipv4(match.group(0)):
@@ -200,6 +208,73 @@ def _changed_paths(base: str) -> list[str]:
)
def _local_changed_paths() -> set[str]:
commands = (
["git", "diff", "--cached", "--name-only", "--diff-filter=ACMR", "-z", "--"],
["git", "diff", "--name-only", "--diff-filter=ACMR", "-z", "--"],
["git", "ls-files", "--others", "--exclude-standard", "-z"],
)
outputs = (
subprocess.run(command, capture_output=True, check=True).stdout
for command in commands
)
return {
value.decode("utf-8")
for output in outputs
for value in output.split(b"\0")
if value
}
HUNK_RE = re.compile(r"^@@ -\d+(?:,\d+)? \+(?P<start>\d+)(?:,(?P<count>\d+))? @@")
def _introduced_lines(base: str, path: str) -> set[int]:
result = subprocess.run(
[
"git",
"diff",
"--no-color",
"--no-ext-diff",
"--unified=0",
"--diff-filter=ACMR",
f"{base}..HEAD",
"--",
path,
],
capture_output=True,
check=True,
text=True,
)
lines: set[int] = set()
for value in result.stdout.splitlines():
match = HUNK_RE.match(value)
if match is None:
continue
start = int(match.group("start"))
count = int(match.group("count") or 1)
lines.update(range(start, start + count))
return lines
def check_changed(base: str) -> list[Finding]:
"""Scan introduced committed lines and all local-only file content."""
local_paths = _local_changed_paths()
findings: list[Finding] = []
for path in _changed_paths(base):
path_findings = scan_file(Path(path), path)
if path in local_paths:
findings.extend(path_findings)
continue
introduced = _introduced_lines(base, path)
findings.extend(
finding
for finding in path_findings
if finding.line == 0 or finding.line in introduced
)
return sorted(set(findings))
def check_paths(paths: Iterable[str]) -> list[Finding]:
findings: list[Finding] = []
for value in paths:
@@ -216,7 +291,11 @@ def main() -> int:
paths = _changed_paths(args.changed_since) if args.changed_since else args.paths
if not paths:
raise ValueError("no paths selected")
findings = check_paths(paths)
findings = (
check_changed(args.changed_since)
if args.changed_since
else check_paths(paths)
)
except (OSError, UnicodeDecodeError, subprocess.SubprocessError, ValueError):
print("share-safety scan failed closed:SCAN_ERROR")
return 2