extracting-credentials-from-memory-dump

Warn

Audited by Socket on Apr 6, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the skill is internally consistent as a credential-forensics guide, but its actual footprint is a high-risk offensive capability for an AI agent: extracting hashes, passwords, tickets, tokens, and cloud credentials from memory. Install sources are mostly legitimate and local data stays local in the examples, so this is not confirmed malware, but it is a dangerous skill that materially enables credential theft/abuse if misused.

Confidence: 93%Severity: 88%
Audit Metadata
Analyzed At
Apr 6, 2026, 11:51 AM
Package URL
pkg:socket/skills-sh/mukul975%2FAnthropic-Cybersecurity-Skills%2Fextracting-credentials-from-memory-dump%2F@5197194eb17b83e21fe2c731ec45dd2ad9e27bbf