yt-music

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill explicitly asks the user to paste full Cookie header values (session tokens) and shows commands that embed that cookie verbatim (e.g., auth setup --cookie ''), forcing the agent to handle and output sensitive secrets directly.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and interprets public YouTube Music content — helper.py calls ytmusicapi for search, charts, related, lyrics and playlist data and player_daemon.py launches a Playwright browser to load music.youtube.com (see SKILL.md and Workflows/PlayDiscover.md/BuildPlaylist.md) — and those external, user-generated pages/results are used to resolve videoIds and drive actions (play, create/add to playlists), so untrusted third‑party content can materially influence the agent's next actions.