style-anchors-collection

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

• Third-party content exposure detected (high risk: 0.90). The skill's interactive collection explicitly accepts and reads external repository URLs (see Step 3.1 "Provide URL to reference repository file" and Step 3.3 "If file is accessible, read and display"), so it will fetch and ingest public third‑party code/pages (e.g., GitHub links) and incorporate that content into generated anchors and task instructions, allowing untrusted content to influence agent behavior.