skills/wgpsec/aboutsecurity/prompt-leak/Socket

prompt-leak

Warn

Audited by Socket on May 4, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS: the skill is purpose-built for system prompt extraction and offensive LLM reconnaissance. It has low supply-chain risk but high inherent abuse potential because its stated goal is to reveal hidden instructions, tools, and security controls from target AI systems.

Confidence: 96%Severity: 84%

Audit Metadata

Analyzed At

May 4, 2026, 08:17 AM

Package URL

pkg:socket/skills-sh/wgpsec%2FAboutSecurity%2Fprompt-leak%2F@e46427bc00acb89770004e7b08785efef6f69781