fix: validate nested Git dependency credentials

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
This commit is contained in:
John Kennedy
2026-08-05 22:36:53 +00:00
co-authored by open-swe[bot] <open-swe@users.noreply.github.com>
parent de9b5216c8
commit b51ef57707
3 changed files with 143 additions and 12 deletions
+54 -12
View File
@@ -6,6 +6,7 @@ import re
import shlex
import textwrap
from collections import Counter
from collections.abc import Iterable
from typing import Literal, NamedTuple
import click
@@ -36,7 +37,10 @@ DISALLOWED_BUILD_COMMAND_CHARS = [
# This blocks background execution (cmd &) while allowing command
# chaining (cmd1 && cmd2) which is common in build commands.
_SINGLE_AMPERSAND_RE = re.compile(r"(?<!&)&(?:&&)*(?!&)")
_GIT_HTTP_AUTHORITY_RE = re.compile(r"git\+https?://(?P<authority>[^/\s]+)", re.I)
_GIT_HTTP_AUTHORITY_RES = (
re.compile(r"git\+https?://(?P<authority>[^/\s\"']+)", re.I),
re.compile(r"\bgit\s*=\s*[\"']https?://(?P<authority>[^/\s\"']+)", re.I),
)
_API_VERSION_PATTERN = re.compile(
r"^(?P<major>\d+)"
r"(?:\.(?P<minor>\d+))?"
@@ -83,10 +87,53 @@ def _has_git_http_url_userinfo(dependency: str) -> bool:
"""Check whether a Git HTTP URL contains userinfo."""
return any(
"@" in match.group("authority")
for match in _GIT_HTTP_AUTHORITY_RE.finditer(dependency)
for pattern in _GIT_HTTP_AUTHORITY_RES
for match in pattern.finditer(dependency)
)
def _validate_git_http_url_userinfo(values: Iterable[str]) -> None:
"""Reject credential-bearing Git HTTP URLs without echoing their values."""
if not any(_has_git_http_url_userinfo(value) for value in values):
return
raise click.UsageError(
"Git dependency URLs must not contain credentials or other URL "
"userinfo because generated Dockerfiles and image layers can retain "
"them. Use a credential-free Git URL and provide short-lived "
"credentials through your build environment's secret-backed Git "
"credential helper."
)
def _validate_git_http_url_userinfo_files(paths: Iterable[pathlib.Path]) -> None:
"""Reject credential-bearing Git HTTP URLs in dependency files."""
contents: list[str] = []
for path in paths:
if not path.is_file():
continue
try:
contents.append(path.read_text(encoding="utf-8", errors="replace"))
except OSError:
raise click.UsageError(
f"Could not inspect dependency file for embedded credentials: {path}"
) from None
_validate_git_http_url_userinfo(contents)
def _validate_local_dependency_files(config_path: pathlib.Path, config: Config) -> None:
"""Validate dependency files copied into a non-uv Python image."""
paths: list[pathlib.Path] = []
for dependency in config["dependencies"]:
if not isinstance(dependency, str) or not dependency.startswith("."):
continue
root = (config_path.parent / dependency).resolve()
paths.extend(
root / name
for name in ("requirements.txt", "pyproject.toml", "setup.py", "setup.cfg")
)
_validate_git_http_url_userinfo_files(paths)
MIN_PYTHON_VERSION = "3.11"
DEFAULT_PYTHON_VERSION = "3.11"
@@ -424,17 +471,11 @@ def validate_config(config: Config) -> Config:
' "source": {"kind": "uv", "root": ".."}'
)
if any(
isinstance(dependency, str) and _has_git_http_url_userinfo(dependency)
_validate_git_http_url_userinfo(
dependency
for dependency in config["dependencies"]
):
raise click.UsageError(
"Git dependency URLs must not contain credentials or other URL "
"userinfo because generated Dockerfiles and image layers can retain "
"them. Use a credential-free Git URL and provide short-lived "
"credentials through your build environment's secret-backed Git "
"credential helper."
)
if isinstance(dependency, str)
)
source = config.get("source")
source_kind = _get_source_kind(config)
@@ -1301,6 +1342,7 @@ def python_config_to_docker(
api_version=api_version,
build_tools_to_uninstall=build_tools_to_uninstall,
)
_validate_local_dependency_files(config_path, config)
if pip_installer == "auto":
if _image_supports_uv(base_image):
pip_installer = "uv"
+10
View File
@@ -880,6 +880,7 @@ def python_config_to_docker_uv_lock(
_get_node_pm_install_cmd,
_get_pip_cleanup_lines,
_image_supports_uv,
_validate_git_http_url_userinfo_files,
docker_tag,
)
@@ -890,11 +891,20 @@ def python_config_to_docker_uv_lock(
)
config_root = config_path.parent.resolve()
source_root = config["source"].get("root", ".")
project_root = (config_root / source_root).resolve()
_validate_git_http_url_userinfo_files(
[project_root / "pyproject.toml", project_root / "uv.lock"]
)
install_cmd = "uv pip install --system"
_, global_reqs_pip_install, pip_config_file_str = _build_python_install_commands(
config, install_cmd
)
plan = _plan_uv_lock_workspace(config_path, config)
_validate_git_http_url_userinfo_files(
package.pyproject_path for package in plan.install_order
)
_update_uv_lock_graph_paths(config_path, config, plan)
for section, key in [
+79
View File
@@ -299,6 +299,85 @@ def test_validate_config_allows_git_urls_without_http_userinfo(dependency: str):
assert config["dependencies"] == [dependency]
def test_config_to_docker_rejects_git_http_url_userinfo_in_requirements(
tmp_path: pathlib.Path,
):
config_path = tmp_path / "langgraph.json"
config_path.write_text("{}\n")
(tmp_path / "agent.py").write_text("graph = object()\n")
(tmp_path / "requirements.txt").write_text(
"private @ git+https://secret-token@github.com/org/private.git\n"
)
config = validate_config(
{
"python_version": "3.11",
"dependencies": ["."],
"graphs": {"agent": "./agent.py:graph"},
}
)
with pytest.raises(click.UsageError) as exc_info:
config_to_docker(
config_path,
config,
base_image="langchain/langgraph-api:0.2.47",
)
message = str(exc_info.value)
assert "must not contain credentials or other URL userinfo" in message
assert "secret-token" not in message
@pytest.mark.parametrize("manifest", ["pyproject.toml", "uv.lock"])
def test_config_to_docker_rejects_git_http_url_userinfo_in_uv_files(
tmp_path: pathlib.Path, manifest: str
):
config_path = tmp_path / "langgraph.json"
config_path.write_text("{}\n")
(tmp_path / "src").mkdir()
(tmp_path / "src" / "agent.py").write_text("graph = object()\n")
pyproject = textwrap.dedent(
"""
[project]
name = "agent"
version = "0.1.0"
dependencies = ["private"]
[tool.uv.sources]
private = { git = "https://github.com/org/private.git" }
"""
).strip()
uv_lock = "# uv lock file\n"
if manifest == "pyproject.toml":
pyproject = pyproject.replace(
"https://github.com", "https://secret-token@github.com"
)
else:
uv_lock += (
'source = { git = "https://secret-token@github.com/org/private.git" }\n'
)
(tmp_path / "pyproject.toml").write_text(pyproject + "\n")
(tmp_path / "uv.lock").write_text(uv_lock)
config = validate_config(
{
"python_version": "3.11",
"graphs": {"agent": "./src/agent.py:graph"},
"source": {"kind": "uv"},
}
)
with pytest.raises(click.UsageError) as exc_info:
config_to_docker(
config_path,
config,
base_image="langchain/langgraph-api:0.2.47",
)
message = str(exc_info.value)
assert "must not contain credentials or other URL userinfo" in message
assert "secret-token" not in message
def test_validate_config_image_distro():
"""Test validation of image_distro field."""
# Valid image_distro values should work