social-engineering

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content contains explicit, actionable instructions for credential theft and data exfiltration (phishing frameworks, Evilginx2/Modlishka reverse proxies, Gophish), MFA/2FA bypass, remote code execution (PowerShell IEX download, Bash Bunny/Rubber Ducky payloads), physical compromise techniques (badge cloning, tailgating), and caller-ID spoofing—clear patterns of deliberate malicious behavior and backdoor/enabling techniques.

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

• Third-party content exposure detected (high risk: 0.90). The skill's reference (reference/social-engineering.md) explicitly instructs cloning and harvesting from arbitrary external sites (e.g., "Enter target URL to clone" in the Social Engineering Toolkit section, Evilginx2 lures/get-url, and watering-hole identification of frequently visited websites), which requires fetching and interpreting untrusted public web content as part of the workflow.