obliteratus
Warn
Audited by Socket on Sep 1, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill is internally consistent, but its purpose is to disable LLM safeguards and it installs/runs a substantial third-party CLI from a personal GitHub repo without strong release verification. No clear credential-harvesting or covert exfiltration is shown, so this looks more like a high-risk capability with moderate supply-chain concerns than confirmed malware.
Confidence: 82%Severity: 62%
Audit Metadata