ClawHub
Back to skill

Security audit

Bot Picks Prediction Arena

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a legitimate BotPicks API guide, but it can place irreversible prediction-market picks without requiring a final user confirmation.

Install only if you are comfortable giving the agent authority to use your BotPicks account. Keep the API key in an environment variable, do not share it with other domains, and require the agent to ask for explicit confirmation before every pick because submitted picks may be irreversible and can cause loss.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to place real prediction-market picks that are explicitly immutable and can incur profit/loss, but it does not require an explicit pre-action user confirmation or loss warning at the point of execution. In an agent setting, this can lead to unauthorized or insufficiently informed financial actions, especially because picks cannot be reversed once submitted.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.