fix(security): redact URL credentials from pip subprocess output before logging

CodeQL flagged 3 clear-text-logging-of-secrets alerts in
install_requirements_file() (src/common/permission_utils.py:353,360,371).
Pre-existing on main, unrelated to this PR's own diff, but now visible
since the path-injection alerts that previously took priority in the
annotation list are fixed.

The underlying risk is real: pip can echo a private index URL's embedded
basic-auth credentials (from a requirements.txt --index-url line or
PIP_INDEX_URL) back verbatim in its own stderr/stdout on failure, and this
function both logs that output directly and returns it to callers --
store_manager.py's _install_dependencies() logs result.stderr from this
same function too.

Added _redact_url_credentials(), applied immediately after each of the two
subprocess.run() calls (mutating result.stderr/stdout in place) rather
than patching each log call site individually. This closes the leak at
the source: every downstream use -- the three flagged log lines, the
"note" string embedded in the returned stdout, and store_manager.py's own
logging of the returned result -- gets the redacted text for free.

Verified the fixed-phrase "denied" check (`"a password is required" in
result.stderr`) is unaffected, since URL syntax and those phrases don't
overlap -- covered explicitly by
test_does_not_touch_denied_check_phrases. Added
test/test_permission_utils.py (6 tests) covering the redaction helper
directly and both subprocess.run() call sites (the sudo-wrapper branch,
which this repo's scripts/fix_perms/safe_pip_install.sh makes live, and
the no-wrapper fallback branch). All pass.

src/common/permission_utils.py

@@ -8,6 +8,7 @@ files that need to be accessible by both root service and web user.
 
 import os
 import logging
+import re
 import shutil as _shutil
 import subprocess
 import sys
@@ -16,6 +17,25 @@ from typing import Optional
 
 logger = logging.getLogger(__name__)
 
+# Matches the credentials portion of a "scheme://user:pass@host" URL, so pip's
+# own error output can be logged/displayed without echoing back a private
+# index URL's embedded basic-auth secret verbatim (e.g. from a
+# requirements.txt --index-url line or the PIP_INDEX_URL env var).
+_URL_CREDENTIALS_RE = re.compile(r'://[^/\s@:]+:[^/\s@]+@')
+
+
+def _redact_url_credentials(text: Optional[str]) -> str:
+    """Replace embedded user:pass@ URL credentials in text with a placeholder.
+
+    Safe to call on any subprocess output destined for logs: it only ever
+    shortens/replaces the credential substring, never changes the presence
+    or absence of the specific fixed phrases callers check for
+    (e.g. "a password is required"), so it can't affect control flow.
+    """
+    if not text:
+        return text or ""
+    return _URL_CREDENTIALS_RE.sub('://***:***@', text)
+
 # System directories that should never have their permissions modified
 # These directories have special system-level permissions that must be preserved
 PROTECTED_SYSTEM_DIRECTORIES = {  # nosec B108 - these are checked to PREVENT permission changes, not to use as temp paths
@@ -338,6 +358,13 @@ def install_requirements_file(req_file: Path, timeout: int = 300) -> subprocess.
                 ["sudo", "-n", bash_path, str(wrapper), str(req_file)],
                 capture_output=True, text=True, timeout=timeout, cwd=str(project_root)
             )
+            # Redact immediately: pip can echo a private index URL's embedded
+            # basic-auth credentials back in its own error/progress output
+            # (e.g. from a requirements.txt --index-url line). Doesn't affect
+            # the fixed-phrase "denied" check below -- those phrases never
+            # overlap with URL syntax.
+            result.stderr = _redact_url_credentials(result.stderr)
+            result.stdout = _redact_url_credentials(result.stdout)
             if result.returncode == 0:
                 return result
             # Distinguish "sudo rejected this exact command line" (worth
@@ -386,6 +413,7 @@ def install_requirements_file(req_file: Path, timeout: int = 300) -> subprocess.
         [sys.executable, "-m", "pip", "install", "--break-system-packages", "--ignore-installed", "-r", str(req_file)],
         capture_output=True, text=True, timeout=timeout, cwd=str(project_root)
     )
-    result.stdout = note + (result.stdout or "")
+    result.stderr = _redact_url_credentials(result.stderr)
+    result.stdout = note + _redact_url_credentials(result.stdout)
     return result
 

test/test_permission_utils.py

@@ -0,0 +1,83 @@
+"""
+Tests for src.common.permission_utils's URL-credential redaction.
+
+Covers the fix for a CodeQL clear-text-logging-of-secrets alert:
+install_requirements_file() must never let a private index URL's embedded
+user:pass@ credentials reach logs or its returned CompletedProcess, since
+pip can echo that URL back verbatim in its own stderr/stdout on failure.
+"""
+
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+from src.common.permission_utils import _redact_url_credentials, install_requirements_file
+
+
+class TestRedactUrlCredentials:
+    def test_redacts_embedded_basic_auth(self):
+        text = "Could not fetch URL https://alice:s3cr3t@pypi.example.com/simple/: 403"
+        redacted = _redact_url_credentials(text)
+        assert "s3cr3t" not in redacted
+        assert "alice" not in redacted
+        assert "https://***:***@pypi.example.com/simple/" in redacted
+
+    def test_leaves_credential_free_text_unchanged(self):
+        text = "ERROR: Could not find a version that satisfies the requirement foo==1.0"
+        assert _redact_url_credentials(text) == text
+
+    def test_handles_none_and_empty(self):
+        assert _redact_url_credentials(None) == ""
+        assert _redact_url_credentials("") == ""
+
+    def test_does_not_touch_denied_check_phrases(self):
+        """The fixed phrases install_requirements_file greps for must survive
+        redaction untouched -- they don't overlap with URL syntax, but this
+        pins that assumption so a regex change can't silently break it."""
+        text = "sudo: a password is required"
+        assert _redact_url_credentials(text) == text
+
+
+class TestInstallRequirementsFileRedaction:
+    @patch('src.common.permission_utils.subprocess.run')
+    def test_wrapper_path_redacts_stderr_and_stdout(self, mock_run, tmp_path):
+        """safe_pip_install.sh exists in this repo, so install_requirements_file
+        takes the sudo-wrapper branch; a failing result must come back
+        with any embedded index-URL credentials already redacted."""
+        req_file = tmp_path / "requirements.txt"
+        req_file.write_text("requests\n")
+
+        mock_run.return_value = MagicMock(
+            returncode=1,
+            stdout="Looking in indexes: https://bob:hunter2@pypi.internal/simple\n",
+            stderr="ERROR https://bob:hunter2@pypi.internal/simple/foo: 401",
+        )
+
+        result = install_requirements_file(req_file, timeout=5)
+
+        assert "hunter2" not in result.stdout
+        assert "hunter2" not in result.stderr
+        assert "https://***:***@pypi.internal" in result.stdout
+        assert "https://***:***@pypi.internal" in result.stderr
+
+    @patch('src.common.permission_utils.subprocess.run')
+    @patch('src.common.permission_utils.Path.exists', return_value=False)
+    def test_no_wrapper_fallback_path_redacts_stderr_and_stdout(self, mock_exists, mock_run, tmp_path):
+        """No safe_pip_install.sh wrapper -> falls straight to the
+        sys.executable pip fallback (the second subprocess.run call site);
+        its result must come back redacted too, independent of the wrapper
+        branch's own redaction above."""
+        req_file = tmp_path / "requirements.txt"
+        req_file.write_text("requests\n")
+
+        mock_run.return_value = MagicMock(
+            returncode=1,
+            stdout="Looking in indexes: https://carol:swordfish@pypi.internal/simple\n",
+            stderr="ERROR https://carol:swordfish@pypi.internal/simple/foo: 401",
+        )
+
+        result = install_requirements_file(req_file, timeout=5)
+
+        assert "swordfish" not in result.stdout
+        assert "swordfish" not in result.stderr
+        assert "https://***:***@pypi.internal" in result.stdout
+        assert "https://***:***@pypi.internal" in result.stderr