ClawHub
Back to skill

Security audit

Foreseek AI

Security checks across malware telemetry and agentic risk

Overview

The skill appears coherent, but it should be reviewed because it can place live Kalshi trades through an agent without clear confirmation or loss-risk guidance.

Install only if you intentionally want an agent to access a Foreseek/Kalshi-connected account. Use a scoped API key if available, start with read-only or demo actions, and require the agent to repeat ticker, side, order type, contract count, and estimated cost before any live trade or cancellation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill provides direct instructions for placing real-money prediction market trades through a connected account, but it does not include any explicit warning that the action may have irreversible financial consequences or require clear user confirmation. In an agent setting, this increases the risk of accidental or impulsive order placement, especially because the examples present trading as a simple single-step API call.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.