seo-optimization

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires auditing arbitrary external websites (see SKILL.md commands like "npx lighthouse https://example.com" and "curl https://yourdomain.com/robots.txt", the input.schema "url" field, and scripts/main.cjs --analyze ), so the agent will fetch and interpret untrusted public web content that can materially influence its decisions.