unattended-run
Warn
Audited by Socket on Oct 19, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally coherent as an unattended workflow helper, but its primary capability is autonomous decision-making and continuation through checkpoints without the user. There is no clear credential theft or malicious exfiltration in the text, yet the reduction of human approval for outward actions and reliance on unspecified downstream skills makes it high operational risk.
Confidence: 87%Severity: 74%
Audit Metadata