ClawHub
Back to skill

Security audit

lottery-cn-research

Security checks across malware telemetry and agentic risk

Overview

This lottery research skill is transparent about its scripts, data fetching, local file use, and gambling-risk caveats, with no hidden persistence or destructive behavior found.

Before installing, be aware that online history fetching contacts public lottery data sites and output paths are controlled by the command arguments. Keep analysis files in a workspace you trust, and treat generated numbers strictly as entertainment or probability research, not as advice to spend money.

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
88% confidence
Finding
The skill documentation advertises operational capabilities to read local files, write output files, and fetch data from online sources, yet the skill declares no permissions. This creates a mismatch between the skill's effective behavior and its declared trust boundary, which can mislead operators and downstream policy enforcement about what the skill may access.

VirusTotal

46/46 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.