social-graph-ranker

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly harvests and ingests user-generated data from public third-party sources—e.g., X API endpoints (GET /2/users/:id/following, followers) and LinkedIn connection exports or browser scraping—as part of its required "Harvest Your Graph" execution step, and then interprets that data to compute rankings and drive outreach actions, which could allow indirect prompt-injection via malicious or crafted profile content.