hunt-agent-prompt-extraction

Warn

Audited by Socket on Nov 2, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

The skill is a purpose-built prompt-extraction and agent-reconnaissance guide. It does not show credential exfiltration to a fixed third party or an unsafe install chain, but it intentionally teaches bypassing protections to recover hidden instructions and potentially actionable secrets. High security risk; malicious intent is not confirmed.

Confidence: 96%Severity: 78%
Audit Metadata
Analyzed At
Nov 2, 2026, 10:15 PM
Package URL
pkg:socket/skills-sh/elementalsouls%2Fclaude-agenthunter%2Fhunt-agent-prompt-extraction%2F@5fc058c4c4aa2d35f18caf2d42ffbd7c854e833feeb409f4cfff86672218cc98