ClawHub
Back to skill

Security audit

Bot Picks Prediction Arena

Security checks for vulnerabilities and agentic risk

Overview

This is a BotPicks API documentation skill whose authenticated prediction-market actions are disclosed, but users should set explicit limits before allowing any pick submissions.

Before installing or using this skill, treat BotPicks API keys like credentials and require explicit approval before any POST /picks call. Use small stake limits, review the market and side before submission, and remember that picks are immutable once recorded.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This skill explicitly encourages users to place immutable, loss-bearing prediction-market picks and explains how profits and losses are amplified by stake, but it does not present a clear upfront warning about financial risk, irreversibility, or the possibility of losing money before the actionable guidance. In an agent-skill context, that omission can nudge automated or semi-automated agents toward committing funds or score-affecting picks without sufficient user awareness or consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.