frontend-inferencer

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly consumes raw signals extracted from web pages (javascript_signals, html_signals, script_urls) and emits detections with source URLs (e.g., "source": "https://example.com"), so untrusted third‑party page content is read and used to drive inference/decisioning.