searching-history
Warn
Audited by Socket on Mar 21, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated purpose is coherent, but the skill's actual implementation hinges on an unverified external `glhf` binary with no confirmed same-org provenance or official install documentation in the evidence. There is no direct proof of credential theft or exfiltration, yet the mandatory concern is high because an unverifiable CLI is entrusted with access to sensitive conversation history and tool logs.
Confidence: 84%Severity: 82%
Audit Metadata