xss-testing

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). Contains explicit malicious techniques including a cookie exfiltration payload, obfuscated execution (eval(atob(...)) and String.fromCharCode), and guidance/tools for automated exploitation—making it high-risk dual-use content that can be directly used to steal data.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs scanning and testing arbitrary external URLs (e.g., "dalfox url 'http://target.com/page?q=test'" and usage of custom payloads) and includes verification steps that require reading/interpreting responses from public websites, which are untrusted third‑party content.