testing-for-sensitive-data-exposure

Warn

Audited by Socket on Apr 7, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

The skill is purpose-aligned as a penetration-testing guide, but it equips an AI agent with offensive security capabilities to enumerate secrets, inspect authenticated responses, and download exposed repositories. There is no clear credential-harvesting endpoint or deceptive data routing, so this is not confirmed malware, but it is a high-risk security skill because it enables impactful real-world security testing actions.

Confidence: 91%Severity: 84%
Audit Metadata
Analyzed At
Apr 7, 2026, 03:17 AM
Package URL
pkg:socket/skills-sh/mukul975%2FAnthropic-Cybersecurity-Skills%2Ftesting-for-sensitive-data-exposure%2F@62d9b9183671f9db0c9774cd294a6b92216b25e0