seo-optimization

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires auditing arbitrary public target URLs (see schemas/input.schema.json "url" and Phase 1 Diagnosis Tools / commands like npx lighthouse https://example.com, curl https://yourdomain.com/robots.txt in SKILL.md), so the agent will fetch and parse untrusted third‑party website content as part of its workflow.