babeliocli-discover

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated reviews from the public Babelio site (see the "Reviews / critiques" section and the required workflow calls like "babeliocli reviews /livres/.../5603"), and those untrusted third-party texts are read and used to summarize or drive decisions (agent recipes), creating an avenue for indirect prompt injection.