youtube-comment-miner

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks the user to paste their YouTube API key into the conversation and shows/uses commands that embed YT_API_KEY=API_KEY (and would likely substitute the real key), which forces the LLM to handle and potentially emit the secret verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and included Python script explicitly fetch user-generated YouTube comments via the YouTube Data API (see fetch_comments/commentThreads.list in the script and references), then analyze and use those comments to generate reports and content ideas—meaning untrusted third-party content is read and can materially influence the agent's outputs and actions.