ClawHub
Back to skill

Security audit

Trade Tracker

Security checks across malware telemetry and agentic risk

Overview

This is a local trade-analysis skill that reads a user-selected CSV and optionally writes a user-selected JSON report.

Before installing, note that trade CSVs may contain sensitive financial history. Use it on files you intend to analyze locally, and specify --output only when you want it to create or overwrite a JSON report at that path.

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
93% confidence
Finding
The skill advertises 'pure local' operation and only reading CSV input, but the usage examples include writing output to analysis.json and the analyzer detected both file_read and file_write capabilities without any declared permissions. Undeclared file access weakens trust boundaries and can let a host invoke the skill with broader filesystem effects than users or reviewers expect.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.