inference-optimizer
Warn
Audited by Socket on Mar 13, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the stated purpose is plausible, but the skill relies on opaque local shell scripts, asks for overly broad bash/rm allowlisting, and returns raw output without review. No clear malicious exfiltration is visible from the snippet alone, but the execution and deletion scope is disproportionate enough to warrant caution.
Confidence: 84%Severity: 72%
Audit Metadata