hivemind-memory
Warn
Audited by Socket on Aug 15, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the core memory-reading behavior is coherent, and the installer appears official, but the skill’s actual footprint is broader than its stated purpose. Org administration, shared raw session access, embeddings downloads, and especially transitive skill pull/push make it a medium-high risk agent capability rather than a narrowly scoped memory helper.
Confidence: 88%Severity: 71%
Audit Metadata