social-media-audit

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

• Third-party content exposure detected (high risk: 0.75). The skill’s required workflow ingests “competitor handles” and “active platforms” and (per its purpose) would fetch/compare real competitor/public social content at runtime, which is outsider-authored free text (e.g., posts/bios/comments from other accounts) that can be included in the LLM context via scraping/browser extraction or API-delivered post text.