social-engineering

Fail

Audited by Socket on Apr 22, 2026

2 alerts found:

SecurityMalware
SecurityMEDIUM
SKILL.md

该技能不是普通信息检索助手,而是明确为社会工程学攻击、钓鱼和凭据相关攻击做准备的进攻型技能。安装来源本身无明显供应链问题,且数据主要流向官方 API,但技能的实际能力与用途直接服务于现实世界攻击,因此应归类为高风险、可疑的进攻性 AI Agent Skill,而非良性开发工具。

Confidence: 95%Severity: 88%
MalwareHIGH
references/social-engineering-techniques.md

This fragment is an overtly malicious attack playbook that provides actionable phishing/pretexting templates, credential-guessing support, OSINT collection guidance, and watering-hole/supply-chain compromise planning. If included in any distributed package, it should be treated as a high-severity supply-chain security incident and removed/quarantined pending full provenance and dependency review.

Confidence: 90%Severity: 100%
Audit Metadata
Analyzed At
Apr 22, 2026, 10:11 AM
Package URL
pkg:socket/skills-sh/wgpsec%2FAboutSecurity%2Fsocial-engineering%2F@43ddab4035db4f39ad69ca6b6b5bc1800fb8b386