From 8c42325921e3cb18b0f04509ef9da790b01e1c31 Mon Sep 17 00:00:00 2001
From: Val Alexander <68980965+BunsDev@users.noreply.github.com>
Date: Wed, 20 May 2026 11:21:31 -0500
Subject: [PATCH 1/2] chore(script): extend check_ai_attribution to scan commit
 messages

The file-content scan only catches attribution checked in to tracked
files. Agents that follow the default `Co-Authored-By: <AI tool>` git
trailer slip past it. Scan commit-message bodies of commits ahead of the
base ref (default origin/main, override via AI_ATTRIBUTION_BASE_REF)
against the same patterns.

Output prefixes commit-message findings with `[commit-msg <sha>]` so
they're distinguishable from file-content hits at a glance. The scan
no-ops when no usable base ref exists (fresh clone, detached HEAD on
the base itself), preserving the existing behavior for that case.

Use --pretty=tformat:%H so each SHA is newline-terminated for the
while-read loop (--pretty=format:%H omits the trailing newline and the
last record would not be read).
---
 script/check_ai_attribution | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/script/check_ai_attribution b/script/check_ai_attribution
index 34b5ee63..3bf37b06 100755
--- a/script/check_ai_attribution
+++ b/script/check_ai_attribution
@@ -33,6 +33,42 @@ for pattern in "${patterns[@]}"; do
     "$pattern" . >> "$tmp" || true
 done
 
+# Commit-message scan. The file-content scan above only catches attribution that
+# lives in tracked files; an agent that follows the default `Co-Authored-By: ...`
+# trailer for git commits would slip past it. Scan commit-message bodies of
+# commits ahead of the base ref (default: origin/main) against the same patterns.
+#
+# Override the base ref with AI_ATTRIBUTION_BASE_REF for CI or non-standard
+# setups. Skips silently when no usable base ref exists (fresh clone, detached
+# HEAD on the base itself, etc.) so the existing file-scan behavior is preserved.
+if git rev-parse --git-dir >/dev/null 2>&1; then
+  base_ref="${AI_ATTRIBUTION_BASE_REF:-}"
+  if [[ -z "$base_ref" ]]; then
+    for candidate in origin/main main origin/master master; do
+      if git rev-parse --verify --quiet "$candidate" >/dev/null; then
+        base_ref="$candidate"
+        break
+      fi
+    done
+  fi
+
+  if [[ -n "$base_ref" ]] && git rev-parse --verify --quiet "$base_ref" >/dev/null; then
+    while IFS= read -r sha; do
+      [[ -z "$sha" ]] && continue
+      body="$(git log -1 --pretty=format:%B "$sha")"
+      for pattern in "${patterns[@]}"; do
+        # Emit one prefixed line per matching message line.
+        if matched="$(printf '%s\n' "$body" | rg --pcre2 --no-line-number --no-filename "$pattern" 2>/dev/null)"; then
+          while IFS= read -r line; do
+            [[ -z "$line" ]] && continue
+            printf '[commit-msg %s] %s\n' "$sha" "$line" >> "$tmp"
+          done <<< "$matched"
+        fi
+      done
+    done < <(git log "$base_ref..HEAD" --pretty=tformat:%H 2>/dev/null || true)
+  fi
+fi
+
 if [[ ! -s "$tmp" ]]; then
   echo "AI attribution guard passed."
   exit 0

From 0163b36ca382aa6e1e4bdc41af0bb5f6274e6652 Mon Sep 17 00:00:00 2001
From: Val Alexander <68980965+BunsDev@users.noreply.github.com>
Date: Wed, 20 May 2026 20:21:01 -0500
Subject: [PATCH 2/2] fix: harden AI_ATTRIBUTION_BASE_REF against option
 injection

---
 script/check_ai_attribution | 39 ++++++++++++++++++++++++-------------
 1 file changed, 25 insertions(+), 14 deletions(-)

diff --git a/script/check_ai_attribution b/script/check_ai_attribution
index 3bf37b06..5a45ad29 100755
--- a/script/check_ai_attribution
+++ b/script/check_ai_attribution
@@ -52,20 +52,31 @@ if git rev-parse --git-dir >/dev/null 2>&1; then
     done
   fi
 
-  if [[ -n "$base_ref" ]] && git rev-parse --verify --quiet "$base_ref" >/dev/null; then
-    while IFS= read -r sha; do
-      [[ -z "$sha" ]] && continue
-      body="$(git log -1 --pretty=format:%B "$sha")"
-      for pattern in "${patterns[@]}"; do
-        # Emit one prefixed line per matching message line.
-        if matched="$(printf '%s\n' "$body" | rg --pcre2 --no-line-number --no-filename "$pattern" 2>/dev/null)"; then
-          while IFS= read -r line; do
-            [[ -z "$line" ]] && continue
-            printf '[commit-msg %s] %s\n' "$sha" "$line" >> "$tmp"
-          done <<< "$matched"
-        fi
-      done
-    done < <(git log "$base_ref..HEAD" --pretty=tformat:%H 2>/dev/null || true)
+  if [[ -n "$base_ref" ]]; then
+    # Reject refs that start with '-' to prevent option injection
+    if [[ "$base_ref" == -* ]]; then
+      echo "AI_ATTRIBUTION_BASE_REF must not start with '-': $base_ref" >&2
+      exit 1
+    fi
+
+    # Resolve to a commit SHA to avoid option injection
+    base_sha=$(git rev-parse --verify --quiet -- "${base_ref}^{commit}" 2>/dev/null) || base_sha=""
+
+    if [[ -n "$base_sha" ]]; then
+      while IFS= read -r sha; do
+        [[ -z "$sha" ]] && continue
+        body="$(git log -1 --pretty=format:%B "$sha")"
+        for pattern in "${patterns[@]}"; do
+          # Emit one prefixed line per matching message line.
+          if matched="$(printf '%s\n' "$body" | rg --pcre2 --no-line-number --no-filename "$pattern" 2>/dev/null)"; then
+            while IFS= read -r line; do
+              [[ -z "$line" ]] && continue
+              printf '[commit-msg %s] %s\n' "$sha" "$line" >> "$tmp"
+            done <<< "$matched"
+          fi
+        done
+      done < <(git log "$base_sha..HEAD" --pretty=tformat:%H 2>/dev/null || true)
+    fi
   fi
 fi