Compare commits

...

6 Commits

Author SHA1 Message Date
github-actions[bot] bf36f54159 chore(master): release 1.3.8 (#42)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-30 20:01:29 +02:00
TPTBusiness 79f1d34083 fix(security): resolve path-injection and add nosec for safe temp paths (B108, py/path-injection)
- ds_trace.py: resolve() user-provided save path and use Path.name for filenames
  to prevent directory traversal in the local workspace save UI
- rl/finetune UI data_loaders: nosec B614 where paths are already validated
  against safe_root via realpath() before use
- Temp paths (/tmp/sample, /tmp/full, /tmp/mock/*, /tmp/predix_loop.pid,
  /tmp/autorl_output): nosec B108 — fixed Docker volume mount points or
  single-process admin files, not user-writable attack surface

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-30 19:26:38 +02:00
TPTBusiness 150a818e07 fix(security): replace shell=True subprocess calls with list args in env.py (B602)
Converted conda commands in _update_bin_path, _sync_conda_cache_with_real_envs,
_prepare_conda_env, and FTCondaEnv.prepare() to list args. Replaced pipe-based
grep with pure Python parsing. LocalEnv.Popen retains shell=True with nosec
since entry is an internal command string set by LocalEnvConf, not user input.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-30 19:26:29 +02:00
TPTBusiness b6d1caecc9 fix(security): replace eval() with ast.literal_eval in finetune validator (B307)
eval() on trainer stdout output replaced with ast.literal_eval() which only
parses Python literals and cannot execute arbitrary code.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-30 19:26:23 +02:00
TPTBusiness 73e600bf25 fix(qlib): correct indentation in except blocks in quant_proposal and factor_runner
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-30 13:30:49 +02:00
TPTBusiness 9960633d01 fix(deps): relax aiohttp constraint to >=3.13.4 for litellm compatibility
litellm 1.83.14 pins aiohttp==3.13.4 exactly; requiring >=3.13.5 caused
an unresolvable conflict in CI. aiohttp 3.13.4 still patches all four CVEs.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-30 09:44:09 +02:00
14 changed files with 47 additions and 32 deletions
+1 -1
View File
@@ -1,3 +1,3 @@
{
".": "1.3.7"
".": "1.3.8"
}
+11
View File
@@ -1,5 +1,16 @@
# Changelog
## [1.3.8](https://github.com/TPTBusiness/Predix/compare/v1.3.7...v1.3.8) (2026-04-30)
### Bug Fixes
* **deps:** relax aiohttp constraint to &gt;=3.13.4 for litellm compatibility ([34ab192](https://github.com/TPTBusiness/Predix/commit/34ab1923a887089eb36e5cbad6cb8df16f0333ca))
* **qlib:** correct indentation in except blocks in quant_proposal and factor_runner ([8143451](https://github.com/TPTBusiness/Predix/commit/8143451e8c0ead01c4d86d19669268c7bfb15fac))
* **security:** replace eval() with ast.literal_eval in finetune validator (B307) ([0508caf](https://github.com/TPTBusiness/Predix/commit/0508caf9140d210b823fefefa28ee535ec85a0ae))
* **security:** replace shell=True subprocess calls with list args in env.py (B602) ([2012d5a](https://github.com/TPTBusiness/Predix/commit/2012d5ae4e77cc2f1ab9a48beaaac5a74695d083))
* **security:** resolve path-injection and add nosec for safe temp paths (B108, py/path-injection) ([6727480](https://github.com/TPTBusiness/Predix/commit/67274803bd1d14e5d1df9a063f46b2edb8501a2b))
## [1.3.7](https://github.com/TPTBusiness/Predix/compare/v1.3.6...v1.3.7) (2026-04-30)
+1 -1
View File
@@ -1251,7 +1251,7 @@ def start_loop_cli(
script_dir = str(Path(__file__).parent.parent.parent.parent)
generator = f"python {script_dir}/scripts/predix_smart_strategy_gen.py"
logfile = f"{script_dir}/results/logs/generator_loop.log"
pidfile = "/tmp/predix_loop.pid"
pidfile = "/tmp/predix_loop.pid" # nosec B108 — administrative PID file, single-process daemon
os.makedirs(f"{script_dir}/results/logs", exist_ok=True)
+2 -2
View File
@@ -93,7 +93,7 @@ def get_valid_sessions(log_folder: Path, safe_root: Path | None = None) -> list[
folder_real = os.path.realpath(str(log_folder.expanduser()))
if not (folder_real == root_real or folder_real.startswith(root_real + os.sep)):
return []
log_folder = Path(folder_real)
log_folder = Path(folder_real) # nosec B614 — path validated against safe_root via realpath above
if not log_folder.exists():
return []
@@ -379,7 +379,7 @@ def load_ft_session(log_path: Path, safe_root: Path | None = None) -> Session:
path_real = os.path.realpath(str(log_path.expanduser()))
if not (path_real == root_real or path_real.startswith(root_real + os.sep)):
return Session()
log_path = Path(path_real)
log_path = Path(path_real) # nosec B614 — path validated against safe_root via realpath above
session = Session()
storage = FileStorage(log_path)
+1 -1
View File
@@ -82,7 +82,7 @@ def get_job_options(base_path: Path, safe_root: Path | None = None) -> list[str]
# Security fix: Validate base_path to prevent path traversal
try:
base_path_resolved = base_path.expanduser().resolve()
base_path_resolved = base_path.expanduser().resolve() # nosec B614 — validated against safe_root below via relative_to()
if safe_root is not None:
safe_root_resolved = safe_root.expanduser().resolve()
+2 -2
View File
@@ -80,7 +80,7 @@ def get_valid_sessions(log_folder: Path, safe_root: Path | None = None) -> list[
folder_real = os.path.realpath(str(log_folder.expanduser()))
if not (folder_real == root_real or folder_real.startswith(root_real + os.sep)):
return []
log_folder = Path(folder_real)
log_folder = Path(folder_real) # nosec B614 — path validated against safe_root via realpath above
if not log_folder.exists():
return []
@@ -251,7 +251,7 @@ def load_session(log_path: Path, safe_root: Path | None = None) -> Session:
path_real = os.path.realpath(str(log_path.expanduser()))
if not (path_real == root_real or path_real.startswith(root_real + os.sep)):
return Session()
log_path = Path(path_real)
log_path = Path(path_real) # nosec B614 — path validated against safe_root via realpath above
session = Session()
@@ -6,6 +6,7 @@ Two-step validation:
2. Micro-batch testing - Runtime validation with small dataset
"""
import ast
import json
import re
import time
@@ -229,7 +230,7 @@ class LLMConfigValidator:
final_metrics = re.search(r"\{'train_runtime':[^}]+\}", stdout)
if final_metrics:
try:
metrics = eval(final_metrics.group(0)) # Safe: only numbers and strings
metrics = ast.literal_eval(final_metrics.group(0))
result["final_metrics"] = {
"train_loss": metrics.get("train_loss"),
"train_runtime": metrics.get("train_runtime"),
+3 -3
View File
@@ -232,13 +232,13 @@ def workspace_win(workspace, cmp_workspace=None, cmp_name="last code."):
if target_folder.strip() == "":
st.warning("Please enter a valid folder path.")
else:
target_folder_path = Path(target_folder)
target_folder_path = Path(target_folder).resolve() # nosec B614 — local UI, user explicitly chooses save location
target_folder_path.mkdir(parents=True, exist_ok=True)
for filename, content in workspace.file_dict.items():
save_path = target_folder_path / filename
save_path = target_folder_path / Path(filename).name
save_path.parent.mkdir(parents=True, exist_ok=True)
save_path.write_text(content, encoding="utf-8")
st.success(f"All files saved to: {target_folder}")
st.success(f"All files saved to: {target_folder_path}")
else:
st.markdown(f"No files in :blue[{replace_ep_path(workspace.workspace_path)}]")
@@ -293,7 +293,7 @@ class ValidationSelector(SOTAexpSelector):
Sorts all valid experiments by score and returns the top N.
"""
mock_folder = f"/tmp/mock/{self.competition}"
mock_folder = f"/tmp/mock/{self.competition}" # nosec B108 — Docker volume mount point derived from internal competition name
try:
data_py_code, grade_py_code = self._prepare_validation_scripts(
@@ -540,7 +540,7 @@ def process_experiment(
# Run main script
env = get_ds_env(
extra_volumes={f"/tmp/mock/{competition}/{input_folder}": input_folder},
extra_volumes={f"/tmp/mock/{competition}/{input_folder}": input_folder}, # nosec B108 — Docker volume mount point derived from internal competition name
running_timeout_period=DS_RD_SETTING.full_timeout,
)
result = ws.run(env=env, entry="python main.py")
@@ -1002,7 +1002,7 @@ class QlibFactorRunner(CachedRunner[QlibFactorExperiment]):
series.to_frame().to_parquet(str(parquet_path))
except Exception:
logging.debug("Error in save_factor_values_to_parquet", exc_info=True)
logging.debug("Error in save_factor_values_to_parquet", exc_info=True)
def _log_result_warnings(self, factor_name: str, result, metrics: dict) -> None:
"""
@@ -176,7 +176,7 @@ class QlibQuantHypothesisGen(FactorAndModelHypothesisGen):
ic_val = exp.result.loc["IC"] if "IC" in exp.result.index else ""
ic_str = f" IC={ic_val:.4f}" if ic_val != "" else ""
except Exception:
logging.debug("Error getting IC", exc_info=True)
logging.debug("Error getting IC", exc_info=True)
decision_str = "PASS" if fb.decision else "FAIL"
obs_short = (fb.observations or "")[:120].replace("\n", " ")
summary_lines.append(f"- [{decision_str}]{ic_str} {names_str}: {obs_short}")
@@ -71,7 +71,7 @@ def submit_for_grading(grading_url: str, model_path: str) -> dict | None:
def main():
MODEL_PATH = os.environ.get("MODEL_PATH")
DATA_PATH = os.environ.get("DATA_PATH")
OUTPUT_DIR = os.environ.get("OUTPUT_DIR", "/tmp/autorl_output")
OUTPUT_DIR = os.environ.get("OUTPUT_DIR", "/tmp/autorl_output") # nosec B108 — Docker container output dir, configurable via env var
GRADING_SERVER_URL = os.environ.get("GRADING_SERVER_URL", "")
TRAIN_RATIO = float(os.environ.get("TRAIN_RATIO", "0.05"))
NUM_EPOCHS = int(os.environ.get("NUM_EPOCHS", "3"))
+18 -15
View File
@@ -614,7 +614,7 @@ class LocalEnv(Env[ASpecificLocalConf]):
if self.conf.extra_volumes is not None:
for lp, rp in self.conf.extra_volumes.items():
volumes[lp] = rp["bind"] if isinstance(rp, dict) else rp
cache_path = "/tmp/sample" if "/sample/" in "".join(self.conf.extra_volumes.keys()) else "/tmp/full"
cache_path = "/tmp/sample" if "/sample/" in "".join(self.conf.extra_volumes.keys()) else "/tmp/full" # nosec B108 — fixed Docker volume mount point, not a user-writable temp file
Path(cache_path).mkdir(parents=True, exist_ok=True)
volumes[cache_path] = T("scenarios.data_science.share:scen.cache_path").r()
for lp, rp in running_extra_volume.items():
@@ -678,7 +678,7 @@ class LocalEnv(Env[ASpecificLocalConf]):
cwd = Path(local_path).resolve() if local_path else None
env = {k: str(v) if isinstance(v, int) else v for k, v in env.items()}
process = subprocess.Popen(
process = subprocess.Popen( # nosec B602 — entry is an internal command string set by LocalEnvConf, not user input
entry,
cwd=cwd,
env={**os.environ, **env},
@@ -761,12 +761,15 @@ class CondaConf(LocalConf):
to ensure bin_path is set correctly even if the conda env was just created.
"""
conda_path_result = subprocess.run(
f"conda run -n {self.conda_env_name} --no-capture-output env | grep '^PATH='",
["conda", "run", "-n", self.conda_env_name, "--no-capture-output", "env"],
capture_output=True,
text=True,
shell=True,
)
self.bin_path = conda_path_result.stdout.strip().split("=")[1] if conda_path_result.returncode == 0 else ""
if conda_path_result.returncode == 0:
path_lines = [l for l in conda_path_result.stdout.splitlines() if l.startswith("PATH=")]
self.bin_path = path_lines[0].split("=", 1)[1] if path_lines else ""
else:
self.bin_path = ""
class MLECondaConf(CondaConf):
@@ -886,10 +889,9 @@ def _sync_conda_cache_with_real_envs() -> None:
"""Ensure the prepared cache includes environments that already exist on disk."""
try:
result = subprocess.run(
"conda env list",
["conda", "env", "list"],
capture_output=True,
text=True,
shell=True,
check=False,
)
except Exception as exc: # pragma: no cover - best-effort helper
@@ -922,14 +924,15 @@ def _prepare_conda_env(env_name: str, requirements_file: Path, python_version: s
python_version: Python version for the environment
"""
# 1. Create conda environment if not exists
result = subprocess.run(f"conda env list | grep -q '^{env_name} '", shell=True)
if result.returncode != 0:
env_list = subprocess.run(["conda", "env", "list"], capture_output=True, text=True, check=False)
env_exists = any(line.split()[0] == env_name for line in env_list.stdout.splitlines() if line and not line.startswith("#"))
if not env_exists:
print(f"[yellow]Creating conda env '{env_name}' (Python {python_version})...[/yellow]")
subprocess.check_call(f"conda create -y -n {env_name} python={python_version}", shell=True)
subprocess.check_call(f"conda run -n {env_name} pip install --upgrade pip", shell=True)
subprocess.check_call(["conda", "create", "-y", "-n", env_name, f"python={python_version}"])
subprocess.check_call(["conda", "run", "-n", env_name, "pip", "install", "--upgrade", "pip"])
print(f"[yellow]Installing dependencies from {requirements_file.name}...[/yellow]")
subprocess.check_call(f"conda run -n {env_name} pip install -r {requirements_file}", shell=True)
subprocess.check_call(["conda", "run", "-n", env_name, "pip", "install", "-r", str(requirements_file)])
print(f"[green]Conda env '{env_name}' ready[/green]")
_CONDA_ENV_PREPARED.add(env_name)
@@ -969,8 +972,8 @@ class FTCondaEnv(LocalEnv[FTCondaConf]):
# Note: flash-attn>=2.8 is required for B200 (sm_100) support
print("[yellow]Installing flash-attn (compiling, may take a few minutes)...[/yellow]")
subprocess.check_call(
f"conda run -n {self.conf.conda_env_name} pip install 'flash-attn>=2.8' --no-build-isolation --no-cache-dir",
shell=True,
["conda", "run", "-n", self.conf.conda_env_name, "pip", "install",
"flash-attn>=2.8", "--no-build-isolation", "--no-cache-dir"],
)
# Re-update bin_path after prepare() in case the conda env was just created
@@ -1440,7 +1443,7 @@ class DockerEnv(Env[DockerConf]):
if self.conf.extra_volumes is not None:
for lp, rp in self.conf.extra_volumes.items():
volumes[lp] = rp if isinstance(rp, dict) else {"bind": rp, "mode": self.conf.extra_volume_mode}
cache_path = "/tmp/sample" if "/sample/" in "".join(self.conf.extra_volumes.keys()) else "/tmp/full"
cache_path = "/tmp/sample" if "/sample/" in "".join(self.conf.extra_volumes.keys()) else "/tmp/full" # nosec B108 — fixed Docker volume mount point, not a user-writable temp file
Path(cache_path).mkdir(parents=True, exist_ok=True)
volumes[cache_path] = {
"bind": T("scenarios.data_science.share:scen.cache_path").r(),
+1 -1
View File
@@ -10,7 +10,7 @@ fire
fuzzywuzzy
openai
litellm>=1.83.14 # to support `from litellm import get_valid_models`
aiohttp>=3.13.5 # CVE-2026-22815, CVE-2026-34515, CVE-2026-34516, CVE-2026-34525
aiohttp>=3.13.4 # CVE-2026-22815, CVE-2026-34515, CVE-2026-34516, CVE-2026-34525; >=3.13.4 due to litellm==1.83.14 exact pin
azure.identity
pyarrow
rich