dense-multi-agent-worktree-delivery
Warn
Audited by Socket on Oct 13, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill’s behavior is mostly aligned with its stated software-delivery purpose, and there is no clear malware or deceptive exfiltration path. However, it grants an AI agent broad authority to coordinate code changes, PR operations, and external status updates across multiple services, which is a substantial operational risk surface and only moderately scoped.
Confidence: 83%Severity: 58%
Audit Metadata