shatter
Warn
Audited by Socket on Oct 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent and not a credential-stealing or supply-chain lure, but it equips an AI agent to conduct disruptive fault-injection and attacker-style testing against real systems. Risk comes from destructive operational capability and weak enforcement of containment, not from hidden installs or exfiltration.
Confidence: 91%Severity: 78%
Audit Metadata