ClawTeam Multi-Agent Coordination
Warn
Audited by Socket on May 2, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally aligned with multi-agent coordination and does not show obvious credential theft or off-platform exfiltration, but it enables high-risk autonomous behavior by default. The main concern is broad, approval-skipping permissions for spawned sub-agents, which is disproportionate for a coordination skill and raises the operational security risk substantially.
Confidence: 85%Severity: 74%
Audit Metadata