page-audit

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow fetches and reads the full rendered content of an outsider-provided URL, and then also reads competitor pages returned from a Google search derived from that input; if the attacker can control the URL submitted to the skill, they effectively supply the free text the LLM ingests.