skills/onewave-ai/claude-skills/agent-army/Socket

agent-army

Warn

Audited by Socket on Apr 10, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS: the skill is coherent as a repo-refactoring orchestrator and shows no obvious exfiltration or supply-chain abuse, but it enables high-autonomy, large-scale agent spawning with broad file and shell access. Risk comes from proportionality and autonomous execution breadth, not confirmed malicious behavior.

Confidence: 90%Severity: 72%

Audit Metadata

Analyzed At

Apr 10, 2026, 05:27 PM

Package URL

pkg:socket/skills-sh/onewave-ai%2Fclaude-skills%2Fagent-army%2F@091c583cd33ebc2e36608aeea86d09dcea0fe2ed