tmdb

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

• Third-party content exposure detected (high risk: 0.70). This skill explicitly fetches and acts on data from the public TMDb API (see SKILL.md commands like search, movie, where, recommend, suggest), which is a third-party, community-populated source that the agent reads and uses to generate recommendations and take actions (e.g., watchlist/suggest), so untrusted content could influence behavior.