Security audit
Hippocampus Subagent Memory
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only guidance skill for isolating sub-agent memory, with no code execution, credential use, or hidden install behavior.
Safe to install as a memory-isolation guide. Users should still review child-agent summaries or artifacts before importing them into parent memory, avoid merging full transcripts, and keep sensitive data out of persistent memory unless they explicitly intend to store it.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
66/66 vendors flagged this skill as clean.