claude-code-skill
Warn
Audited by Socket on May 3, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
The skill's capabilities mostly match its stated purpose as a multi-engine coding-session orchestrator, and the documented vendor CLIs are broadly consistent with that purpose. Main risks come from third-party orchestration over multiple authenticated AI tools, optional prompt/raw-body logging, and high-autonomy modes like councils and bypassPermissions. This looks more like a high-powered but risky developer automation skill than confirmed malicious behavior.
Confidence: 80%Severity: 61%
Audit Metadata