xss-reflected

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly requires collecting and reporting "new credentials or tokens found" and saving evidence files (e.g., ssrf-aws-creds.json), which forces the agent to handle and output secret values verbatim, creating an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill file is an explicit playbook for exploiting reflected XSS—providing payloads and techniques to execute arbitrary JavaScript in victims' browsers, exfiltrate cookies/credentials, install keyloggers/phishing UI, and bypass CSP/WAFs—showing clear malicious intent and guidance for data theft and remote abuse.