From 3c488688d1287c1ca89a4a185f8665a5ac5a7b3b Mon Sep 17 00:00:00 2001
From: bradautomates <bradley_bonanno@outlook.com>
Date: Sat, 9 May 2026 08:13:32 +1000
Subject: [PATCH] Harden subprocess argv against option injection (#2)

- download.py: insert `--` before URL in yt-dlp argv so a `-`-prefixed
  string can never be parsed as a flag (e.g. --exec, --config-location).
  Tighten is_url to reject `-`-prefixed sources and require non-empty
  netloc.
- frames.py, whisper.py: resolve video/audio paths to absolute via
  Path.resolve() before passing to ffmpeg/ffprobe (which don't honor
  `--` as end-of-options), so a relative path starting with `-` can
  never be misinterpreted as a flag.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---
 scripts/download.py | 5 ++++-
 scripts/frames.py   | 4 ++--
 scripts/whisper.py  | 4 ++--
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/scripts/download.py b/scripts/download.py
index 4d3429a..589123c 100755
--- a/scripts/download.py
+++ b/scripts/download.py
@@ -18,8 +18,10 @@ VIDEO_EXTS = {".mp4", ".mkv", ".webm", ".mov", ".m4v", ".avi", ".flv", ".wmv"}
 
 
 def is_url(source: str) -> bool:
+    if source.startswith("-"):
+        return False
     parsed = urlparse(source)
-    return parsed.scheme in ("http", "https")
+    return parsed.scheme in ("http", "https") and bool(parsed.netloc)
 
 
 def resolve_local(path: str) -> dict:
@@ -78,6 +80,7 @@ def download_url(url: str, out_dir: Path) -> dict:
         "--no-playlist",
         "--ignore-errors",
         "-o", output_template,
+        "--",
         url,
     ]
 
diff --git a/scripts/frames.py b/scripts/frames.py
index 04e7933..01d205a 100755
--- a/scripts/frames.py
+++ b/scripts/frames.py
@@ -66,7 +66,7 @@ def get_metadata(video_path: str) -> dict:
             "-print_format", "json",
             "-show_format",
             "-show_streams",
-            video_path,
+            str(Path(video_path).resolve()),
         ],
         capture_output=True,
         text=True,
@@ -162,7 +162,7 @@ def extract(
         cmd += ["-to", f"{end_seconds:.3f}"]
 
     cmd += [
-        "-i", video_path,
+        "-i", str(Path(video_path).resolve()),
         "-vf", f"fps={fps},scale={resolution}:-2",
         "-frames:v", str(max_frames),
         "-q:v", "4",
diff --git a/scripts/whisper.py b/scripts/whisper.py
index 565994f..318b449 100755
--- a/scripts/whisper.py
+++ b/scripts/whisper.py
@@ -93,13 +93,13 @@ def extract_audio(video_path: str, out_path: Path) -> Path:
         "-hide_banner",
         "-loglevel", "error",
         "-y",
-        "-i", video_path,
+        "-i", str(Path(video_path).resolve()),
         "-vn",
         "-acodec", "libmp3lame",
         "-ar", "16000",
         "-ac", "1",
         "-b:a", "64k",
-        str(out_path),
+        str(out_path.resolve()),
     ]
     result = subprocess.run(cmd, capture_output=True, text=True)
     if result.returncode != 0: