Hippocampus Memory Core
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This instruction-only memory skill is coherent and purpose-aligned, but users should be mindful that it is meant to store and restore durable agent memory.
Before installing, make sure you are comfortable with the agent storing durable project facts and prior decisions. Avoid storing secrets or raw transcripts, and use the skill’s own scoping guidance: namespace memory by workspace and agent, mark project/task boundaries, and restore only into the correct scope.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Information placed into this memory may be reused later, including during future coding or workspace tasks.
The skill intentionally creates durable memory that can persist across turns or sessions, so stored facts may later influence agent behavior.
Use this skill when you need long-term memory that survives the current turn.
Store only high-value, non-sensitive facts, keep memory namespaced by project or agent, and review restores before applying them to an active workspace.