gpu-resource-utilization-daily-summary
Warn
Audited by Socket on Jul 28, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
BENIGN in purpose and behavior, but SUSPICIOUS from a trust perspective because it requires an unverifiable local `dce` binary. The skill itself is tightly scoped and read-only, with no evident credential harvesting or exfiltration, yet the unresolved CLI provenance forces a high security-risk classification.
Confidence: 87%Severity: 72%
Audit Metadata