meta-content-audit

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

• Third-party content exposure detected (high risk: 0.90). The skill requires the consultant to collect and provide social-media analytics and user-generated content (e.g., posts, "Notable comments or reactions") from third‑party platforms such as Meta Business Suite, TikTok Business Centre, YouTube Studio, LinkedIn/X analytics and instructs the agent to read and base audit decisions on that content, which exposes the agent to untrusted, user-generated input that could carry indirect prompt injection.