narrative-validator

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

• Third-party content exposure detected (high risk: 0.90). The skill's "VALIDATION DES LIENS" and "Vérification des références et liens" requirements force the agent to use the Browser to visit and read every URL in an episode's references (arbitrary public third‑party websites), which clearly ingests untrusted external content and could enable indirect prompt injection.