ClawHub
Back to skill

Security audit

market-heatmap

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed market-data renderer that uses one API key-backed request and writes a local static HTML snapshot without trading or account actions.

Install only if you are comfortable providing a SentiSense API key to this skill and allowing it to make HTTPS requests to SentiSense and write local HTML/JSON output files. Treat the generated board as delayed research data, not trading advice.

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 clearly requires sensitive capabilities at runtime: reading an API key from the environment, making outbound network requests to a third-party service, and writing a generated HTML file to disk. However, the manifest does not declare these operational permissions, which creates a transparency and policy-enforcement gap: hosts may under-evaluate the risk, fail to sandbox appropriately, or expose users to unexpected file/network behavior.

VirusTotal

48/48 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.