linkedin-personal-branding

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly automates a browser to load and snapshot LinkedIn pages (e.g., linkedin.com/in/[user], linkedin.com/in/[user]/recent-activity/, linkedin.com/analytics/, linkedin.com/sales/ssi) and parses profile posts, activity and comments — i.e., untrusted, user-generated third‑party content — as part of its analysis, creating a clear vector for indirect prompt injection.