ClawHub
Back to skill

Security audit

polymarket-fast-loop

Security checks across malware telemetry and agentic risk

Overview

This skill is an automated trading tool whose code can place trades, but its documented paper-trading and governance safeguards are not implemented in the artifact.

Only install this if you intentionally want an autonomous trading script with access to a funded or simulated trading API. Before use, verify where SIMMER_API_URL points, whether that backend can place real orders, and add or require explicit dry-run/live controls, trade limits, and auditable governance checks matching the documentation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding
The skill advertises multiple safety and governance properties—15-minute market support, direct Polymarket trading behavior, ACTA receipts, and Cedar policy enforcement—that the static analysis says are not actually implemented. In a trading skill with financial_actions and network_access, this mismatch is dangerous because operators may rely on nonexistent controls and route real trades through a different backend than expected.

Intent-Code Divergence

High
Confidence
95% confidence
Finding
The file advertises itself as 'Paper Trading' while it can execute real buy orders through the trade endpoint. In a trading skill, that mismatch is dangerous because operators may run it under the assumption that it is simulation-only, causing unintended live trades and financial loss.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill automatically places trades once internal conditions are met, without any explicit user confirmation, safety interlock, or kill switch in the execution path. In the context of an autonomous trading agent with external signals and imported decision modules, this increases the risk of unintended or manipulated trades and direct financial harm.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.