ClawHub
Back to skill

Security audit

ta-chart-basics

Security checks across malware telemetry and agentic risk

Overview

This is a static educational chart-reading skill with no executable behavior or hidden access requests.

Before installing, treat this as an educational technical-analysis basics skill rather than trading advice. The only notable issue is that one test case may route a candlestick OHLC question poorly, but the skill itself does not perform actions or access private data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The edge-case prompt asks how to read a single candlestick's OHLC values, but the expected behavior instead pivots to point-and-figure concepts or another skill. This misalignment can cause incorrect routing or misleading evaluation, making the agent appear correct when it fails the user's actual chart-reading request.

VirusTotal

48/48 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.