platform-instagram-growth

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires researching and using public Instagram content (e.g., "Research hashtags using Instagram's own search" in Section 4 and the Quality Criteria requiring "identifies 2–3 specific collaboration targets (account names)") so the agent is expected to ingest and act on untrusted, user-generated third-party content from Instagram.