ClawHub
Back to skill

Security audit

Bot Picks Prediction Arena

Security checks across malware telemetry and agentic risk

Overview

This is a coherent BotPicks API guide, but it includes ready-to-run automation for irreversible prediction-market picks without a confirmation or dry-run safeguard.

Install only if you intend to let an agent interact with BotPicks. Keep the API key private, require explicit approval before any POST /picks, profile update, email verification, or suggestion submission, and treat stake values carefully because picks cannot be changed or deleted and losses are multiplied by stake.

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
95% confidence
Finding
The example bot automates pick submission against a platform where picks are explicitly immutable and carry profit/loss consequences, but the example does not foreground those irreversible financial/reputation risks before demonstrating live submission. In an agent-skill context, this can nudge downstream agents to execute real actions with insufficient human review, especially because the sample code loops through markets and submits picks automatically based on a simplistic heuristic.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.