nmap-service-detection

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run nmap_script_scan and related NSE scripts (e.g., http-title, http-headers, banner, ssl-cert) against arbitrary targets and then consume the returned results/vulnerability_findings JSON to drive service identification and scan decisions, which means the agent will read untrusted third‑party content (web pages, banners, certs) from arbitrary hosts.