yichen-agent-memory
Warn
Audited by Socket on Sep 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s overall purpose is coherent for a memory-vault admin runbook, and most file/config access is proportionate. The main issue is install trust: it asks the agent to clone and run scripts from a personal GitHub repo, and the referenced installer filenames do not match the surfaced official docs, creating a meaningful supply-chain inconsistency even without clear exfiltration behavior.
Confidence: 88%Severity: 72%
Audit Metadata