cve-2026-31431-copy-fail
Warn
Audited by Socket on Apr 30, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS/HIGH-RISK skill. Its behavior is internally consistent with its stated purpose, but that purpose is to arm an AI agent with local privilege-escalation capability and optional root-shell execution. There is no obvious network exfiltration or hidden credential harvesting, so this is not confirmed malware, but it is an offensive exploit skill with significant security risk.
Confidence: 94%Severity: 88%
Audit Metadata