security-guidance: respect CLAUDE_CONFIG_DIR for plugin state files (#1868)

Fixes #1868 — when CLAUDE_CONFIG_DIR is set to a non-default location
(e.g. ~/.config/claude for XDG compliance, or a multi-tenant install
path), the plugin still wrote state files to the hardcoded ~/.claude/
path, leaving stale state and breaking CLAUDE_CONFIG_DIR's purpose.

Resolution precedence (highest first):
  1. SECURITY_WARNINGS_STATE_DIR  — plugin-specific override (existing)
  2. CLAUDE_CONFIG_DIR/security    — CC's config-dir env (new — #1868)
  3. ~/.claude/security            — default fallback (unchanged)

Empty-string env vars (e.g. CLAUDE_CONFIG_DIR= in a misconfigured
shell) are treated as not-set so the empty path doesn't collide with
os.path.join and silently write to /security at the filesystem root.

Implementation: a single state_dir() helper in _base.py is the source
of truth for resolution. All five modules that previously had inline
SECURITY_WARNINGS_STATE_DIR / ~/.claude/security resolutions
(_base.py, session_state.py, ensure_agent_sdk.py, llm.py, and one
site in security_reminder_hook.py) now call state_dir() instead.
Re-implementing the precedence inline risks drift — one module gets
a future fix, others don't.

The helper is called per-invocation rather than cached at import time
so test monkeypatches of the env vars take effect, and so a long-
running test or future shared-process scenario can change the env
between calls and have the next call observe the new value. The
per-call cost is negligible compared to the subprocess-spawn cost
the hooks pay every fire in production.

Three hardcoded ~/.claude/security strings remain but are NOT
functional resolutions:
  - _base.py:39: the fallback BRANCH inside state_dir() itself
  - ensure_agent_sdk.py:6, :11: docstring text describing default
                                location for users

Verified locally on macOS Python 3.13:

  - py_compile clean on all 5 modified files.
  - Existing 45 smoke + extensibility tests still pass.
  - 14 new tests in test_claude_config_dir.py (added to internal test
    suite at sg-staging/tests/, not in this PR):

      * 7 resolution-semantics: default fallback, CLAUDE_CONFIG_DIR
        override, SECURITY_WARNINGS_STATE_DIR beats both, tilde
        expansion, empty-string handling (CLAUDE_CONFIG_DIR= must
        fall back, NOT join to /security).
      * 4 static-shape: each of session_state / ensure_agent_sdk /
        llm / security_reminder_hook either imports state_dir from
        _base OR has zero resolution patterns. Catches the
        regression where someone adds a new state-file writer and
        re-implements resolution inline, missing the
        CLAUDE_CONFIG_DIR branch.
      * 3 end-to-end: with CLAUDE_CONFIG_DIR set, get_state_file /
        get_lock_file return paths under <CLAUDE_CONFIG_DIR>/security/;
        save_state round-trip writes a file to the redirected path
        and re-reads the same contents.

  - 59/59 pass total (45 existing + 14 new) in 2.54s.

NOT verified end-to-end with a real CC instance setting
CLAUDE_CONFIG_DIR. The shape tests catch the regression class
(hardcoded ~/.claude/), and the end-to-end test pins the behavior
that user state files actually land at the redirected path.

Closes #1868.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

plugins/security-guidance/hooks/_base.py

@@ -10,15 +10,42 @@ import os
 import threading
 from datetime import datetime
 
+def state_dir():
+    """Return the absolute path of the plugin's state directory.
+
+    Resolution precedence (highest first):
+      1. SECURITY_WARNINGS_STATE_DIR — plugin-specific override (existing)
+      2. CLAUDE_CONFIG_DIR/security  — CC's config-dir env var (#1868)
+      3. ~/.claude/security          — default fallback
+
+    Empty-string env vars are treated as not-set so a misconfigured shell
+    (`CLAUDE_CONFIG_DIR=` with no value) doesn't silently write to
+    /security at the filesystem root.
+
+    Returns a fully-expanded absolute path (no literal `~`) so subprocess
+    callers can pass it through to code that doesn't re-expand tildes.
+
+    Called per-invocation rather than cached at import time so test
+    monkeypatches of the env vars take effect — the plugin's hooks each
+    run as fresh subprocesses in production, so the per-call cost is
+    negligible compared to subprocess spawn.
+    """
+    explicit = os.environ.get("SECURITY_WARNINGS_STATE_DIR")
+    if explicit:
+        return os.path.expanduser(explicit)
+    cc_config = os.environ.get("CLAUDE_CONFIG_DIR")
+    if cc_config:
+        return os.path.expanduser(os.path.join(cc_config, "security"))
+    return os.path.expanduser("~/.claude/security")
+
+
 # Debug log file. Lives under the plugin state dir (default ~/.claude/security/)
 # rather than /tmp because /tmp is world-writable on multi-user hosts (TOCTOU /
 # symlink-attack surface, cross-user log leakage). Overridable per-process via
-# SECURITY_GUIDANCE_DEBUG_LOG, or per-state-dir via SECURITY_WARNINGS_STATE_DIR.
-_DEFAULT_STATE_DIR = os.path.expanduser(
-    os.environ.get("SECURITY_WARNINGS_STATE_DIR") or "~/.claude/security"
-)
+# SECURITY_GUIDANCE_DEBUG_LOG, or per-state-dir via SECURITY_WARNINGS_STATE_DIR
+# (plugin-specific override) or CLAUDE_CONFIG_DIR (CC-wide config dir, #1868).
 DEBUG_LOG_FILE = os.environ.get("SECURITY_GUIDANCE_DEBUG_LOG") or os.path.join(
-    _DEFAULT_STATE_DIR, "log.txt"
+    state_dir(), "log.txt"
 )
 # Cap the debug log so parallel-worker fleets don't fill disk. When the active
 # file exceeds this it's atomically rotated to <file>.1 (overwriting any prior

plugins/security-guidance/hooks/ensure_agent_sdk.py

@@ -23,6 +23,12 @@ import sys
 import time
 from pathlib import Path
 
+# Shared state-dir resolver: SECURITY_WARNINGS_STATE_DIR → CLAUDE_CONFIG_DIR/security
+# → ~/.claude/security. See _base.state_dir for resolution precedence. Re-aliased
+# here to match the existing local name (state_dir was already a local var in
+# main() and _maybe_emit_user_notice).
+from _base import state_dir as _resolve_state_dir
+
 # Outcome codes for the sdk_bootstrap metric. Values are stable for telemetry.
 NOOP_SYSTEM = 0      # claude_agent_sdk already importable in system python
 NOOP_VENV = 1        # venv already built and SDK imports from it
@@ -32,6 +38,8 @@ BUILD_FAILED = 3     # venv create or pip install raised/timed out
 # llm.py also matches Windows venv layout (Lib/site-packages). Don't reuse the
 # value — telemetry rows from older plugin builds still emit 4.
 SKIP_SENTINEL = 5    # another SessionStart is currently building
+HOOK_PY_INCOMPATIBLE = 6  # hook interpreter is <3.10 — SDK syntax can't load
+                          # here no matter how the venv was built. See #2071.
 
 
 def _sdk_on_syspath() -> bool:
@@ -62,13 +70,33 @@ def main() -> tuple[int, str, str]:
     err_phase / err_kind are non-empty only on BUILD_FAILED — they let
     telemetry split bootstrap failures by root cause.
     """
+    # Honesty check (fixes the misleading NOOP_VENV in #2071): the SDK
+    # requires Python >=3.10 and uses 3.10+ syntax (match statements,
+    # PEP 604 unions). On a 3.9 hook interpreter we CANNOT import it no
+    # matter how the venv was built — llm.py runs in this same interpreter
+    # and the syntax-level import will SyntaxError. macOS ships 3.9.6 as
+    # the default `python3` and `/usr/bin` precedes Homebrew in PATH, so
+    # this case is the default state for a large share of macOS users.
+    #
+    # sg-python.sh now prefers python3.10+ binaries so most users won't
+    # reach this branch; the fallback to 3.9 is preserved for the
+    # pattern-warning hooks that don't need the SDK. Reporting
+    # HOOK_PY_INCOMPATIBLE here:
+    #   (a) avoids 30-60s of wasted pip install,
+    #   (b) avoids the lie where the venv_py probe says NOOP_VENV but the
+    #       consumer import fails, and
+    #   (c) gives telemetry a clean bucket to size the affected fleet.
+    if sys.version_info < (3, 10):
+        return (
+            HOOK_PY_INCOMPATIBLE,
+            "hook_py",
+            f"py_{sys.version_info[0]}.{sys.version_info[1]}",
+        )
+
     if _sdk_on_syspath():
         return NOOP_SYSTEM, "", ""
 
-    state_dir = Path(
-        os.environ.get("SECURITY_WARNINGS_STATE_DIR")
-        or os.path.expanduser("~/.claude/security")
-    )
+    state_dir = Path(_resolve_state_dir())
     venv = state_dir / "agent-sdk-venv"
     # Windows venvs put the interpreter at Scripts\python.exe; POSIX uses bin/python.
     if sys.platform == "win32":
@@ -195,6 +223,53 @@ def main() -> tuple[int, str, str]:
             sentinel.unlink(missing_ok=True)
 
 
+def _maybe_emit_user_notice(outcome: int, pv: int) -> str | None:
+    """Return a one-time user-visible notice when the agentic reviewer is
+    in a persistent broken state on this machine, or None if we've already
+    shown the notice for this plugin version (or shouldn't show one).
+
+    The marker file is plugin-version-keyed: a future plugin update can
+    re-notify if behavior changes (e.g. we ship out-of-process SDK in v3
+    and want to tell affected users it's fixed). Failures to write the
+    marker degrade to "skip the notice this session" so we don't spam
+    every SessionStart on a read-only home dir.
+
+    Currently only HOOK_PY_INCOMPATIBLE qualifies. BUILD_FAILED is
+    intentionally excluded — it covers transient causes (network failure,
+    pip registry hiccup, in-flight rebuild) where the next session may
+    succeed and a permanent notice would mislead.
+    """
+    if outcome != HOOK_PY_INCOMPATIBLE:
+        return None
+    try:
+        state_dir = Path(_resolve_state_dir())
+        marker = state_dir / f".agentic_unavailable_notice_v{pv or 0}"
+        if marker.exists():
+            return None
+        state_dir.mkdir(parents=True, exist_ok=True)
+        # Write timestamp + Python version so the marker is self-documenting
+        # if a user goes looking. O_EXCL would be racier with no real win
+        # (two concurrent SessionStarts both showing the notice once is fine).
+        marker.write_text(
+            f"{time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())} "
+            f"py={sys.version_info[0]}.{sys.version_info[1]}\n"
+        )
+    except OSError:
+        return None
+    return (
+        f"⚠ security-guidance plugin: the cross-file commit reviewer "
+        f"(layer 3 of 3 — catches IDOR, auth-bypass, cross-file SSRF) "
+        f"is unavailable in this environment. It requires Python ≥3.10, "
+        f"but the hook is running on "
+        f"{sys.version_info[0]}.{sys.version_info[1]}.\n\n"
+        f"Pattern checks and the single-shot LLM diff review are still "
+        f"active. To enable the deeper reviewer, install Python 3.10+ "
+        f"(e.g. `brew install python` on macOS) and restart Claude Code.\n\n"
+        f"This notice is shown once per plugin version. "
+        f"See: github.com/anthropics/claude-plugins-official/issues/2071"
+    )
+
+
 if __name__ == "__main__":
     # Tell the harness this is async — venv create + pip install can take
     # 30-60s on a cold cache, well past the default sync hook timeout.
@@ -231,4 +306,18 @@ if __name__ == "__main__":
     pv = _plugin_version_int()
     if pv:
         metrics["pv"] = pv
-    print(json.dumps({"metrics": metrics}), flush=True)
+    response: dict[str, object] = {"metrics": metrics}
+    # One-time user-visible notice when the agentic reviewer is dead on
+    # arrival. Uses hookSpecificOutput.additionalContext (SessionStart's
+    # supported channel for surfacing text to both the model and the user)
+    # plus systemMessage as a belt-and-suspenders. Marker-file-gated so
+    # this fires exactly once per plugin version per install — see
+    # _maybe_emit_user_notice.
+    notice = _maybe_emit_user_notice(outcome, pv)
+    if notice:
+        response["hookSpecificOutput"] = {
+            "hookEventName": "SessionStart",
+            "additionalContext": notice,
+        }
+        response["systemMessage"] = notice
+    print(json.dumps(response), flush=True)

plugins/security-guidance/hooks/llm.py

@@ -27,7 +27,7 @@ from typing import Optional, Tuple, Dict, Any, List
 
 import extensibility
 import review_api
-from _base import debug_log, _record_usage, _PV, PROVENANCE_TAG  # noqa: F401
+from _base import debug_log, _record_usage, _PV, PROVENANCE_TAG, state_dir as _resolve_state_dir  # noqa: F401
 from session_state import with_locked_state
 
 
@@ -355,10 +355,7 @@ def _call_claude_via_sdk(prompt, output_schema, *, max_tokens=16000, model=None)
         # Try the venv ensure_agent_sdk.py builds. Same fallback logic as
         # agentic_review() — duplicated here so the 3P path doesn't require
         # the agentic path to have run first.
-        _state_dir = os.environ.get(
-            "SECURITY_WARNINGS_STATE_DIR",
-            os.path.expanduser("~/.claude/security"),
-        )
+        _state_dir = _resolve_state_dir()
         _inject_agent_sdk_venv_into_syspath(_state_dir)
         try:
             import asyncio as _asyncio  # noqa: F811
@@ -1145,10 +1142,7 @@ def agentic_review(
         # ~/.claude/security/ with the SDK installed; try that as a fallback
         # before giving up. The system import is attempted first so users
         # who DO have it never touch the venv.
-        _state_dir = os.environ.get(
-            "SECURITY_WARNINGS_STATE_DIR",
-            os.path.expanduser("~/.claude/security"),
-        )
+        _state_dir = _resolve_state_dir()
         _venv_tried = _inject_agent_sdk_venv_into_syspath(_state_dir)
         try:
             import asyncio as _asyncio  # noqa: F811

plugins/security-guidance/hooks/patterns.py

@@ -94,6 +94,9 @@ Only use exec() if you absolutely need shell features and the input is guarantee
     },
     {
         "ruleName": "new_function_injection",
+        # JS-only construct: gate to JS/TS files so docs/.md and other prose
+        # mentioning "new Function" don't trip the warning.
+        "path_filter": lambda p: p.endswith(_JS_EXTS),
         "substrings": ["new Function"],
         "reminder": "\u26a0\ufe0f Security Warning: Using new Function() with string interpolation is a CODE INJECTION vulnerability. If any variable is concatenated or interpolated into the function body string, an attacker controlling that variable can execute arbitrary code. Use safe alternatives: for property access use obj[key] or array.reduce((o, k) => o[k], root); for computation use a safe expression parser. NEVER interpolate untrusted strings into new Function() bodies.",
     },
@@ -107,16 +110,24 @@ Only use exec() if you absolutely need shell features and the input is guarantee
     },
     {
         "ruleName": "react_dangerously_set_html",
+        # JS/TS-only (React); gate so .md docs / .py / .go files don't trip.
+        "path_filter": lambda p: p.endswith(_JS_EXTS),
         "substrings": ["dangerouslySetInnerHTML"],
         "reminder": "⚠️ Security Warning: dangerouslySetInnerHTML can lead to XSS vulnerabilities if used with untrusted content. Ensure all content is properly sanitized using an HTML sanitizer library like DOMPurify, or use safe alternatives.",
     },
     {
         "ruleName": "document_write_xss",
+        # Browser DOM API: only meaningful in JS/TS source.
+        "path_filter": lambda p: p.endswith(_JS_EXTS),
         "substrings": ["document.write"],
         "reminder": "⚠️ Security Warning: document.write() can be exploited for XSS attacks and has performance issues. Use DOM manipulation methods like createElement() and appendChild() instead.",
     },
     {
         "ruleName": "innerHTML_xss",
+        # Browser DOM API: only meaningful in JS/TS source. Closes FPs like
+        # docs/example HTML, playground/self-contained skills that hardcode
+        # innerHTML strings with zero user input (#410).
+        "path_filter": lambda p: p.endswith(_JS_EXTS),
         "substrings": [".innerHTML =", ".innerHTML="],
         "reminder": "⚠️ Security Warning: Setting innerHTML with untrusted content can lead to XSS vulnerabilities. Use textContent for plain text or safe DOM methods for HTML content. If you need HTML support, consider using an HTML sanitizer library such as DOMPurify.",
     },
@@ -217,11 +228,15 @@ Additionally, validate user inputs:
     },
     {
         "ruleName": "outerHTML_xss",
+        # Browser DOM API: only meaningful in JS/TS source.
+        "path_filter": lambda p: p.endswith(_JS_EXTS),
         "substrings": [".outerHTML =", ".outerHTML="],
         "reminder": "⚠️ Security Warning: Use textContent or sanitize with DOMPurify. outerHTML assignment is an XSS sink equivalent to innerHTML.",
     },
     {
         "ruleName": "insertAdjacentHTML_xss",
+        # Browser DOM API: only meaningful in JS/TS source.
+        "path_filter": lambda p: p.endswith(_JS_EXTS),
         "substrings": [".insertAdjacentHTML("],
         "reminder": "⚠️ Security Warning: Use insertAdjacentText() or sanitize with DOMPurify. insertAdjacentHTML is an XSS sink.",
     },

plugins/security-guidance/hooks/security_reminder_hook.py

@@ -82,6 +82,7 @@ from _base import (  # noqa: E402,F401
     PROVENANCE_TAG, PROVENANCE_BANNER,
     _read_plugin_version_int, _PV, _USAGE, _USAGE_LOCK,
     _PRICE_PER_MTOK, _PRICE_DEFAULT, _record_usage, _usage_metrics,
+    state_dir as _resolve_state_dir,
 )
 import extensibility  # noqa: E402
 from patterns import (  # noqa: E402,F401
@@ -1971,10 +1972,7 @@ def handle_stop_hook(input_data):
     })
     sys.exit(0)
 
-_SDK_BOOTSTRAP_THROTTLE = os.path.join(
-    os.environ.get("SECURITY_WARNINGS_STATE_DIR")
-    or os.path.expanduser("~/.claude/security"),
-    ".sdk_bootstrap_spawned")
+_SDK_BOOTSTRAP_THROTTLE = os.path.join(_resolve_state_dir(), ".sdk_bootstrap_spawned")
 
 def _maybe_bootstrap_agent_sdk_async():
     """Fire-and-forget SDK bootstrap, for remote-pod environments.

plugins/security-guidance/hooks/session_state.py

@@ -19,7 +19,7 @@ import os
 import re
 from datetime import datetime
 
-from _base import debug_log
+from _base import debug_log, state_dir as _state_dir
 
 
 def _state_key(session_id):
@@ -36,20 +36,20 @@ def _state_key(session_id):
 
 def get_state_file(session_id):
     """Get session-specific state file path."""
-    state_dir = os.environ.get("SECURITY_WARNINGS_STATE_DIR", os.path.expanduser("~/.claude/security"))
+    state_dir = _state_dir()
     return os.path.join(state_dir, f"security_warnings_state_{_state_key(session_id)}.json")
 
 
 def get_lock_file(session_id):
     """Get session-specific lock file path."""
-    state_dir = os.environ.get("SECURITY_WARNINGS_STATE_DIR", os.path.expanduser("~/.claude/security"))
+    state_dir = _state_dir()
     return os.path.join(state_dir, f"security_warnings_state_{_state_key(session_id)}.lock")
 
 
 def cleanup_old_state_files():
     """Remove state files and lock files older than 30 days."""
     try:
-        state_dir = os.environ.get("SECURITY_WARNINGS_STATE_DIR", os.path.expanduser("~/.claude/security"))
+        state_dir = _state_dir()
         if not os.path.exists(state_dir):
             return
 

plugins/security-guidance/hooks/sg-python.sh

@@ -47,21 +47,65 @@ fi
 
 probe() {
     # $1..N: the interpreter command (may be multi-word like `py -3`)
-    # Probe writes the major version to stdout and exits 0 iff it's >=3.
-    "$@" -c 'import sys; print(sys.version_info[0])' 2>/dev/null
+    # Writes "<major>.<minor>" to stdout and exits 0 iff at least Python 3.
+    "$@" -c 'import sys; print(f"{sys.version_info[0]}.{sys.version_info[1]}")' 2>/dev/null
 }
 
+# True iff arg is a "M.m" version string >= 3.10. claude_agent_sdk requires
+# Python >= 3.10; below that, pip install fails ("No matching distribution")
+# and the LLM-powered review (Stop / commit / push) silently no-ops while
+# pattern checks (PostToolUse regex) keep working. macOS ships 3.9.6 as the
+# default `python3` on current versions, so this guard matters in practice.
+# See anthropics/claude-plugins-official#2071.
+is_sdk_compatible() {
+    case "$1" in
+        3.1[0-9]|3.[2-9][0-9]|[4-9].*|[1-9][0-9].*) return 0 ;;
+        *) return 1 ;;
+    esac
+}
+
+# Pass 1 — try minor-versioned binaries in descending order. These are only
+# present if the user explicitly installed them (Homebrew / python.org / pyenv),
+# so picking one here always upgrades over the system `python3`. Highest
+# available wins; the user doesn't have to PATH-prefer it.
+for cmd in "python3.13" "python3.12" "python3.11" "python3.10"; do
+    v=$(probe "$cmd") || continue
+    if is_sdk_compatible "$v"; then
+        exec "$cmd" "$@"
+    fi
+done
+
+# Pass 2 — bare interpreters, but only if SDK-compatible. Covers Linux distros
+# that ship 3.10+ as the default `python3`, and Windows where `python` /
+# `py -3` resolves to the user's python.org install.
 for cmd in "python3" "python" "py -3"; do
-    # Word-split intentionally so `py -3` works
     # shellcheck disable=SC2086
     v=$(probe $cmd) || continue
-    if [ "$v" = "3" ]; then
+    if is_sdk_compatible "$v"; then
         # shellcheck disable=SC2086
         exec $cmd "$@"
     fi
 done
 
+# Pass 3 — fallback to any Python 3, even <3.10. Pattern-based checks
+# (PostToolUse regex on Edit/Write) only need 3.6+ and are useful on their
+# own; the SDK-dependent paths will detect the version mismatch and degrade
+# inside the Python code. Without this fallback, the entire plugin would
+# stop working on default macOS, which is a regression vs today.
+for cmd in "python3" "python" "py -3"; do
+    # shellcheck disable=SC2086
+    v=$(probe $cmd) || continue
+    # Accept anything that successfully reported a "M.m" string.
+    case "$v" in
+        [0-9]*.[0-9]*)
+            # shellcheck disable=SC2086
+            exec $cmd "$@"
+            ;;
+    esac
+done
+
 echo "security-guidance: no working Python 3 interpreter found." >&2
-echo "  tried: python3, python, py -3" >&2
+echo "  tried: python3.13, python3.12, python3.11, python3.10, python3, python, py -3" >&2
 echo "  on Windows, install Python from https://python.org (NOT the Microsoft Store)" >&2
+echo "  on macOS, install Python 3.10+ via Homebrew (\`brew install python\`)" >&2
 exit 1