scan

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

• Third-party content exposure detected (high risk: 0.90). Yes — the SKILL.md explicitly directs the agent to fetch and analyze responses from arbitrary external targets (Steps 2–5: nmap NSE scripts, nikto, sqlmap, curl and HTTP endpoint testing), and to adapt subsequent actions based on those findings, meaning untrusted public content can influence tool use and decisions.