lighthouse-audit

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

• Third-party content exposure detected (high risk: 0.90). The skill runs Lighthouse against arbitrary URLs supplied to the audit and batch commands (see run_lighthouse and the batch/audit CLI handlers which read URLs from user input or urls.txt) and ingests the resulting JSON/report content from public websites, exposing the agent to untrusted third‑party page content that could carry indirect prompt injection.