ClawHub
Back to skill

Security audit

LYGO Emotional RAM

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local text-analysis and optional memory-index tool with disclosed consent-gated writes and no network or subprocess behavior found.

Before installing, understand that indexing creates a local memory file and may preserve sensitive labels or vectors; do not index secrets, API keys, PHI, or private material unless you intentionally control where the state file is stored. Avoid --store-plaintext except on a private host.

SkillSpector

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

Static analysis

No suspicious patterns detected.