arabench
Warn
Audited by Socket on Nov 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The stated benchmarking purpose is coherent and the skill itself contains no apparent exfiltration instructions or malicious behavior. However, it requires a CLI whose provenance is not verified by the available evidence, creating elevated supply-chain risk.
Confidence: 85%Severity: 75%
Audit Metadata