Pentest Commands
Warn
Audited by Socket on Jul 28, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s behavior matches its stated pentesting purpose, but that purpose is to equip an AI agent with offensive security actions including exploitation, brute forcing, reverse-shell payload generation, and data extraction. There is little evidence of credential harvesting or deceptive routing, so this is not confirmed malware, but it is a high-risk capability set for an AI skill.
Confidence: 91%Severity: 86%
Audit Metadata