youtube-data-api

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

• Third-party content exposure detected (high risk: 0.85). The skill calls the YouTube Data API at runtime and ingests the returned JSON fields (e.g., snippet.title, snippet.description, and especially commentThreads/replies text) into the CLI output/LLM context; these text fields are authored by third parties (YouTube users), making them outsider free text.