HTML Injection Testing

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill content contains explicit, actionable instructions for creating phishing overlays, hijacking forms, and exfiltrating credentials and cookies to third‑party attacker domains (e.g., attacker.com), demonstrating deliberate malicious intent and high abuse potential.

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 the agent to fetch and inspect arbitrary public web pages (e.g., curl examples and the "Custom Fuzzing Script" that uses requests.get against http://target.com and to grep/inspect response.text) so it ingests untrusted third-party content and uses that content to drive testing decisions and next actions.