memory-management
Warn
Audited by Socket on Oct 16, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core memory behavior is purpose-aligned, but the skill’s footprint is broader than a normal memory helper: it installs/runs an external CLI/MCP server, uses session API credentials for hook classification, silently captures transcript data, and auto-generates future skills. The inconsistent publisher/install identity adds supply-chain uncertainty, so this is not confirmed malware but it is a medium-high risk skill.
Confidence: 84%Severity: 76%
Audit Metadata