Security audit
Hippocampus Openclaw Onboarding
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only onboarding skill for connecting OpenClaw to Hippocampus memory, with expected credential and local configuration steps disclosed.
Before running the setup command, verify the `hipokamp-mcp` package and gateway are legitimate, prefer a scoped bootstrap token over a long-lived API key, and use separate Hippocampus workspaces for unrelated projects.
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
57/57 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.