ClawHub
Back to skill

Security audit

LYGO Sovereign Super Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed LYGO stack advisor and command map, with local checks and consent-gated stack operations rather than hidden execution.

Before installing, understand that this skill is mainly an operational map: some listed LYGO stack commands can modify local stack files, and publish or push commands should only be run when you explicitly ask for them. Set LYGO_STACK_ROOT only to the intended LYGO clone and review commands before consenting to any planter or publishing step.

SkillSpector

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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill advertises operational commands that read environment variables and local files (for example LYGO_STACK_ROOT, registry paths, and self_check.py behavior) but does not declare corresponding permissions. That mismatch can cause users or agents to grant trust under incomplete information, and in adversarial scenarios hidden file/environment access can be abused to inspect sensitive local paths or configuration.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.