youtube-content-strategist

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to check memory for and ask the user to "please paste your key" and shows running the script with an inline YT_API_KEY=API_KEY command, which encourages the LLM to receive and/or embed the API key verbatim (and store it in memory), creating a direct secret-exfiltration risk.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches user-generated content from the public YouTube Data API v3 (playlistItems.list, videos.list, search.list) — ingesting video titles, tags, and statistics — and then analyzes that untrusted content to produce strategy recommendations and a 30-day calendar, so third-party content can materially influence decisions and actions.