ClawHub
Back to skill

Security audit

industry-prosperity-tracker

Security checks across malware telemetry and agentic risk

Overview

This skill coherently fetches public financial and macro data, calculates an industry score, and writes a local report without hidden persistence or credential use.

Install only if you are comfortable with a finance skill running local Python scripts, installing/using AKShare, fetching public market and macro data online, and writing report files locally. Treat the output as research support, not investment advice, and avoid feeding untrusted names or JSON into the HTML report generator.

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
83% confidence
Finding
The skill instructs the agent to run local scripts that read templates/references and write JSON/HTML outputs, but the manifest does not declare corresponding permissions. Undeclared file access weakens least-privilege controls and can lead to unauthorized reads/writes or make downstream reviewers underestimate the skill’s capabilities.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.