memory-fabric
Warn
Audited by Socket on Oct 23, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s stated purpose and most capabilities are coherent for a memory-retrieval internals guide, and there is no clear credential harvesting or exfiltration path. However, it depends on an unpinned npx-installed MCP package whose official Anthropic provenance could not be verified, which creates a substantial supply-chain and transitive trust risk disproportionate to a documentation-style skill.
Confidence: 85%Severity: 72%
Audit Metadata