ClawHub

Simul8or Trader

Security checks across malware telemetry and agentic risk

Overview

This looks like a real simulator-trading skill, but it enables persistent autonomous trading with limited control, cleanup, and credential-safety guidance.

Install only if you intentionally want an autonomous simulator bot that can run every 5 minutes, persist after restart, and place trades on your Simul8or account. Before enabling it, verify the npm package source, use a dedicated simulator-only API key, decide trade limits, and make sure you know how to remove the cron job, stop PM2 startup persistence, delete the local state files, and revoke the API key.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to write to files in the user's home directory, including ~/price-history.jsonl and ~/commands.json, without warning the user that local state will be created or overwritten. This is dangerous because an autonomous skill can persist data, alter future agent behavior, and clobber existing files in a sensitive per-user location.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The setup flow tells users to transmit personal registration data and later use an API key, but provides no warning about credential sensitivity, storage risks, or privacy implications. Even though HTTPS is used, the lack of guidance increases the chance of users exposing secrets in shell history, config files, logs, or sharing the skill without understanding data handling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal