agent-architect
Warn
Audited by Socket on Mar 30, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill’s orchestration role is coherent, but its footprint is broad for an agent skill because it autonomously launches background agents, executes generated project scripts, and can perform external publication actions. No clear malware or credential-harvesting behavior is present, and install sources are mostly standard, but the autonomous execution and arbitrary generated-script runtime make it medium risk.
Confidence: 82%Severity: 59%
Audit Metadata