ClawHub

Fear Greed

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward crypto Fear & Greed widget and CLI with disclosed external market-data fetching and no evidence of hidden access, persistence, or harmful behavior.

Reasonable to install if you trust the Strykr API/CDN endpoints. For production dashboards, treat the hosted script or iframe like any third-party web dependency, and make sure curl and jq are available before using the shell command.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding
The skill advertises embeddable React/HTML components, but the documented behavior includes shell execution, raw JSON/CLI output, and outbound calls to a remote PRISM service. This mismatch can mislead users and agents into granting trust or integrating the skill under false assumptions, increasing the risk of unexpected code execution paths and unreviewed data exfiltration or supply-chain exposure via remote dependencies.

Missing User Warnings

Low
Confidence
93% confidence
Finding
The script silently performs a network request to an external service to retrieve market sentiment data, with no user-facing notice that data is fetched from a remote endpoint. While this appears necessary for the widget's functionality and not overtly malicious, undisclosed outbound requests can surprise users, create privacy/compliance issues, and expose environments to dependency on an external service that may be unavailable or changed.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrase "market sentiment" is generic enough to match many unrelated finance or analysis requests, which can cause the skill to activate outside the user's intended context. In an agent environment, unintended invocation can expose users to irrelevant external data retrieval or cause workflow hijacking toward this skill when another tool would be more appropriate.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal