super-ralph-wiggum
Warn
Audited by Socket on Oct 26, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is purpose-aligned as an autonomous coding loop, but its defining capability is unattended repeated action with self-directed task selection and background execution. No clear credential theft or external exfiltration is visible, so it is not malicious on the provided evidence; however, the AFK autonomy and reliance on unseen local scripts make it a high operational-security risk skill.
Confidence: 88%Severity: 74%
Audit Metadata