ClawHub
Back to skill

Security audit

Vegas T Trading

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed trading-analysis skill that runs a local Python market-data analyzer, with financial-risk caveats but no evidence of hidden trading, credential access, or destructive behavior.

Install only if you want a local technical-analysis helper. Run it without elevated privileges, preferably in a virtual environment with pinned dependencies, and expect queried symbols to be sent to market-data providers. Treat all buy/sell, confidence, and position-size language as educational analysis only; do not connect it to brokerage automation or trade solely from its output.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
76% confidence
Finding
The trigger description includes broad phrases such as general trading-related queries, which can cause the skill to activate in contexts the user did not intend. Over-broad invocation increases the chance of unplanned external data access and financial-advice-style responses without sufficiently specific user consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal