jw-player

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md) instructs the agent to use Membrane actions and the proxy (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint") to fetch data from the JW Player API and list/get media and playlists, which are third-party, potentially user-generated content that the agent is expected to read and could materially influence subsequent actions.