ClawHub
Back to skill

Security audit

LYGO Haven Star Chart Agent Portal

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, consent-gated helper for validating and submitting Haven Star Chart entries using a trusted local LYGO stack.

Install only if you intend to use this LYGO Haven Star Chart workflow and can point LYGO_STACK_ROOT at a trusted local lygo-protocol-stack clone. Review the security and contract references, run the self-check first, and approve --i-consent submit or ingest commands only when you understand the pending queue or ledger changes they will make.

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
86% confidence
Finding
The skill advertises restrictive capabilities in metadata, but the documented workflow includes shell commands, environment-variable dependence (`LYGO_STACK_ROOT`), and filesystem reads of local stack files. This mismatch is dangerous because agents or reviewers may rely on incomplete permission declarations and grant trust to a skill that can influence local execution flow and access local content beyond what is explicitly declared.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/_stack_tools.py:30