From 46319a53ff24e125ef314d4b010d31a4acf2fb3d Mon Sep 17 00:00:00 2001
From: test <test@test>
Date: Wed, 15 Apr 2026 20:08:35 +0200
Subject: [PATCH] Add grammar security audit and enhance vendor script

- vendor-grammar.sh: copy extra headers (.h, .inc) and common/ subdirs
  from grammar src/ directories. Needed for Astro (tag.h), PureScript/
  Typst (unicode.h), VHDL (.h/.inc files), F# (common/scanner.h).

- audit-grammar-security.sh: pre-vendoring scanner for dangerous patterns
  in vendored grammar C files. Checks for dangerous includes (sys/*,
  unistd.h, dlfcn.h), dangerous calls (system, exec, popen, fopen,
  socket, getenv, fork, dlopen), and suspicious patterns (constructor
  attributes, inline assembly, base64 blobs). PASS/WARN/BLOCK per grammar.
---
 scripts/audit-grammar-security.sh | 105 ++++++++++++++++++++++++++++++
 scripts/vendor-grammar.sh         |  11 ++++
 2 files changed, 116 insertions(+)
 create mode 100755 scripts/audit-grammar-security.sh

diff --git a/scripts/audit-grammar-security.sh b/scripts/audit-grammar-security.sh
new file mode 100755
index 000000000..6cc335fc1
--- /dev/null
+++ b/scripts/audit-grammar-security.sh
@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# audit-grammar-security.sh — Scan vendored tree-sitter grammar scanner.c
+# files for dangerous patterns that could indicate malicious code.
+#
+# Grammars are third-party C source compiled into our binary. parser.c files
+# are auto-generated (low risk), but scanner.c files are hand-written C with
+# access to memory allocation and input text.
+#
+# Usage: scripts/audit-grammar-security.sh [directory]
+#   Default: internal/cbm/vendored/grammars/
+
+ROOT="$(cd "$(dirname "$0")/.." && pwd)"
+GRAMMAR_DIR="${1:-$ROOT/internal/cbm/vendored/grammars}"
+
+if [ ! -d "$GRAMMAR_DIR" ]; then
+    echo "ERROR: directory not found: $GRAMMAR_DIR" >&2
+    exit 1
+fi
+
+echo "=== Grammar Security Audit ==="
+echo "Scanning: $GRAMMAR_DIR"
+echo ""
+
+TOTAL=0
+WARNED=0
+BLOCKED=0
+
+# Safe includes that scanners legitimately use
+SAFE_INCLUDES='string\.h|stdint\.h|stdbool\.h|stdlib\.h|wctype\.h|stdio\.h|stddef\.h|limits\.h|assert\.h|ctype\.h|wchar\.h|math\.h|stdalign\.h|stdarg\.h|float\.h|inttypes\.h'
+
+# Dangerous includes
+DANGER_INCLUDES='unistd\.h|sys/|netdb\.h|dlfcn\.h|signal\.h|spawn\.h|pthread\.h|fcntl\.h|dirent\.h|termios\.h|arpa/|netinet/'
+
+# Dangerous function calls
+DANGER_CALLS='system\s*\(|exec[lvpe]+\s*\(|popen\s*\(|fopen\s*\(|fwrite\s*\(|socket\s*\(|getenv\s*\(|fork\s*\(|dlopen\s*\(|connect\s*\(|bind\s*\(|listen\s*\(|accept\s*\(|sendto\s*\(|recvfrom\s*\(|mmap\s*\(|mprotect\s*\('
+
+# Suspicious patterns
+SUSPICIOUS='__attribute__\s*\(\s*\(\s*constructor|__attribute__\s*\(\s*\(\s*destructor|asm\s*\(|__asm__|__asm\b'
+
+for grammar_dir in "$GRAMMAR_DIR"/*/; do
+    name=$(basename "$grammar_dir")
+    TOTAL=$((TOTAL + 1))
+    issues=""
+
+    for src in "$grammar_dir"scanner.c "$grammar_dir"scanner.cc "$grammar_dir"*.h "$grammar_dir"*.inc; do
+        [ -f "$src" ] || continue
+        basename_src=$(basename "$src")
+
+        # Skip tree_sitter/ subdirectory headers (those are standard)
+        case "$src" in
+            */tree_sitter/*) continue ;;
+        esac
+
+        # Check dangerous includes
+        while IFS= read -r line; do
+            issues="${issues}  WARN  $basename_src: dangerous include: $line\n"
+        done < <(grep -nE "#include\s*<($DANGER_INCLUDES)" "$src" 2>/dev/null || true)
+
+        # Check dangerous calls
+        while IFS= read -r line; do
+            issues="${issues}  BLOCK $basename_src: dangerous call: $line\n"
+        done < <(grep -nE "$DANGER_CALLS" "$src" 2>/dev/null || true)
+
+        # Check suspicious patterns
+        while IFS= read -r line; do
+            issues="${issues}  BLOCK $basename_src: suspicious pattern: $line\n"
+        done < <(grep -nE "$SUSPICIOUS" "$src" 2>/dev/null || true)
+
+        # Check for base64-like long encoded strings (40+ alphanumeric chars)
+        while IFS= read -r line; do
+            issues="${issues}  WARN  $basename_src: possible encoded data: $line\n"
+        done < <(grep -nE '"[A-Za-z0-9+/]{60,}={0,2}"' "$src" 2>/dev/null || true)
+    done
+
+    if [ -n "$issues" ]; then
+        if echo -e "$issues" | grep -q "BLOCK"; then
+            echo "BLOCK $name:"
+            echo -e "$issues"
+            BLOCKED=$((BLOCKED + 1))
+        else
+            echo "WARN  $name:"
+            echo -e "$issues"
+            WARNED=$((WARNED + 1))
+        fi
+    fi
+done
+
+echo "────────────────────────────────────────────"
+echo "  Scanned: $TOTAL grammars"
+echo "  Clean:   $((TOTAL - WARNED - BLOCKED))"
+echo "  Warned:  $WARNED"
+echo "  Blocked: $BLOCKED"
+echo "────────────────────────────────────────────"
+
+if [ "$BLOCKED" -gt 0 ]; then
+    echo ""
+    echo "FAILED: $BLOCKED grammar(s) have dangerous patterns. Review before vendoring."
+    exit 1
+fi
+
+echo ""
+echo "PASSED: No dangerous patterns found."
+exit 0
diff --git a/scripts/vendor-grammar.sh b/scripts/vendor-grammar.sh
index 06db85e2f..83009f2ff 100755
--- a/scripts/vendor-grammar.sh
+++ b/scripts/vendor-grammar.sh
@@ -48,6 +48,17 @@ if [ -d "$SRC_DIR/tree_sitter" ]; then
     cp "$SRC_DIR/tree_sitter/"*.h "$GRAMMAR_DIR/tree_sitter/" 2>/dev/null || true
 fi
 
+# Copy any extra headers (.h, .inc files) used by scanners
+# Examples: tag.h (Vue/Svelte/Astro), unicode.h (PureScript/Typst),
+# TokenTree.h/.inc (VHDL)
+for f in "$SRC_DIR"/*.h "$SRC_DIR"/*.inc; do
+    [ -f "$f" ] && cp "$f" "$GRAMMAR_DIR/"
+done
+# Copy common/ subdirectory if present (e.g., F# scanner uses common/scanner.h)
+if [ -d "$SRC_DIR/common" ]; then
+    cp -r "$SRC_DIR/common" "$GRAMMAR_DIR/"
+fi
+
 # Copy LICENSE file from upstream repo
 REPO_ROOT="$TMPDIR/repo"
 if [ -n "$SUBDIR" ]; then