auto-task
Warn
Audited by Socket on Sep 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's stated purpose matches autonomous task orchestration, but its footprint is overly broad: unrestricted Bash, arbitrary MCP tools, external content ingestion, sub-agents, and background execution with limited user interruption. There is no direct malware or credential-stealing behavior, but the combination creates high operational risk and weak data-flow assurance for a generic 'auto-task' skill.
Confidence: 87%Severity: 76%
Audit Metadata