dialogue

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

• Third-party content exposure detected (high risk: 1.00). Flagged because the skill explicitly requires using the Browser to search and ingest web content (including Google Images and YouTube) and to include external reference URLs—e.g., the sections instructing "Utilise l'outil Browser", "Recherche activement des images... Google Images", and "YouTube"—so the agent will fetch and read untrusted public third‑party content.