content-marketing

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and acts on user-generated social content—for example the social-strategy orchestrator routes to "social-listening" (veille, mentions, sentiment), the community-management agent handles comments/DMs and UGC reposts, and the Ligne Éditoriale workflow WF-LE-002 calls for "Collecte: Extraction échantillon contenus (20-50 par canal)"—so the agent will read and base moderation/strategy/response actions on untrusted public social media/forum content, creating a clear risk of indirect prompt injection.