file-path-traversal
Warn
Audited by Socket on Jun 2, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent, but its stated purpose is to help an AI agent perform offensive exploitation, including credential file access and RCE escalation against remote systems. Install trust is relatively normal, yet the operational capability is high-risk and disproportionate for general agent use.
Confidence: 95%Severity: 90%
Audit Metadata