web-vuln-scan

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content is an offensive-oriented web exploitation playbook: it gives actionable steps to obtain RCE, upload webshells, steal credentials/SECRET_KEYs, brute-force default logins, and use SSRF to exfiltrate cloud metadata—clear guidance that can be used for malicious compromise and data exfiltration.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs fetching and interpreting responses from arbitrary target URLs (e.g., "curl -sI http://target", "httpx -u http://target", "nuclei -u http://target", "ffuf -u http://target/FUZZ"), which are untrusted third‑party web content that the agent must read and whose responses directly influence subsequent scanning and exploitation actions.