ClawHub
Back to skill

Security audit

lygo-lpis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local prompt-analysis workflow with consent gates and no evidence of hidden upload, destructive behavior, or automatic remote changes.

Install only if you intend to analyze prompts you own or are authorized to use. Before ingesting, read the security docs, use the required authorization flag, keep the local prompt vault private, and inspect the external LYGO stack tools referenced by the setup instructions before running them.

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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Static analysis

No suspicious patterns detected.