attack-surface-xss

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and analyzes arbitrary target URLs (Phase 1: "Retrieve response headers and page content from $ARGUMENTS") and also fetches external JavaScript files from same-origin and public CDNs (jsdelivr, cdnjs, unpkg, googleapis) — i.e., it ingests untrusted, user-provided third‑party web content that the agent reads and interprets.