lexi
Warn
Audited by Socket on Apr 29, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the stated purpose and local file flows are mostly coherent for a lexicon-analysis skill, and there is no explicit credential collection or network routing. However, it requires execution of an unverifiable bundled `honne` script with unclear provenance, so install/execution trust is not established and overall risk remains high despite limited visible data exfiltration.
Confidence: 82%Severity: 74%
Audit Metadata