auto-task
Warn
Audited by Socket on May 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s stated purpose matches autonomous task orchestration, but its footprint is very broad for a generic workflow skill. The main risk is not malware or credential theft; it is underconstrained autonomy with web/sub-agent/MCP ingestion plus Bash and file-write access, which creates meaningful prompt-injection and unsafe-action exposure.
Confidence: 88%Severity: 74%
Audit Metadata