Security audit
Lpxpoly
Security checks for vulnerabilities and agentic risk
Overview
This skill has a plausible purpose, but it asks the agent to run an undeclared remote npm MCP package with a spend-capable Lightning token.
Before installing, inspect or request the source/tarball for `lpxpoly-mcp`, use a low-balance or scoped spend token for testing, and require explicit confirmation before any paid analysis calls.
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.