ClawHub
Back to skill

Security audit

LYGO Agent Lattice (Layer E — Living Agent Network)

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local Python wrapper for a LYGO agent presence and gossip network, with consent and security limits described in the artifacts.

Install only if you intend to run LYGO stack Python tools and possibly expose a local or shared agent hub. Keep hubs bound to localhost unless intentionally public, set the documented hub token for shared hubs, and review the LYGO stack path you place in LYGO_STACK_ROOT because the wrappers execute named tools from that local stack.

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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill invokes shell commands and depends on environment variables, but the manifest does not declare permissions for those capabilities. This creates a trust and review gap: operators may install or run the skill without understanding that it can execute local commands and consume sensitive environment data, which increases the risk of accidental overexposure or misuse in agent platforms that rely on declared permissions for enforcement.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.