ClawHub
Back to skill

Security audit

LYGO Universal Living Memory Library (v1.2)

Security checks across malware telemetry and agentic risk

Overview

This skill is a local memory-index audit and archive helper whose file access and outputs are disclosed and aligned with its purpose.

Before installing, make sure LYGO_AUTHORITY_ROOT points only at the intended LYGO workspace. Review any MASTER_ARCHIVE.md before minting or public anchoring, especially FRAGILE entries, because hashes and paths can still reveal private project structure even when file contents are not copied.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill advertises executable commands and operational workflows that read environment variables and access local files, yet it does not declare any permissions or capability boundaries. This creates a trust and transparency gap: an agent or user may invoke the skill without realizing it can inspect authority-root paths and write outputs such as MASTER_ARCHIVE.md, increasing the risk of unintended data exposure or filesystem modification.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The document instructs users to 'anchor it publicly' after minting a master archive, but provides no warning that the archive may contain sensitive logs, conversation exports, or personal data. In a memory/continuity library context, this increases the risk of unintended public disclosure of confidential or identifying information because users are explicitly encouraged to publish compressed records.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.