skills/noorqureshi/sploitagent/ai-prompt-injection/Socket

ai-prompt-injection

Warn

Audited by Socket on Sep 20, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS: The skill is internally consistent as a security-testing guide, but its actual purpose is to equip an AI agent to perform prompt-injection attacks, extract system prompts, and validate exfil/tool abuse on targets. There are no install, credential-forwarding, or supply-chain concerns here; the main risk is the offensive capability itself.

Confidence: 96%Severity: 83%

Audit Metadata

Analyzed At

Sep 20, 2026, 11:02 PM

Package URL

pkg:socket/skills-sh/noorqureshi%2Fsploitagent%2Fai-prompt-injection%2F@9d2b3b372a616e7ec710d7377ef6cfbd484918020770c5623db7cc1d7b8cf882