ClawHub
Back to skill

Security audit

Polymarket News Events

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed automated Polymarket news-trading skill that defaults to dry-run and only places trades when live mode is explicitly used.

Install only if you intend to run an automated trading workflow. Keep it in dry-run until you have reviewed the code and configured trade size, venue, thresholds, and any external account limits; live mode can place real trades using the Simmer API key.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The manifest advertises an automaton that monitors RSS feeds and can trade, but it does not declare the sensitive capabilities it clearly relies on: environment access for API keys, network access for feeds and trading APIs, and file read/write for local state in /tmp. Missing permission declarations reduce transparency and can bypass user/operator expectations about what the skill is allowed to access, which is especially risky for an automated trading workflow.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The description frames the skill primarily as a news-monitoring and matching tool, but the actual behavior includes live trade execution, additional market-analysis API calls, and persistence of deduplication state. This mismatch is dangerous because operators may enable or install the skill without realizing it can place real trades or write local state, leading to financial loss or unintended operational exposure.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The manifest uses broad autonomous monitoring and trading language without defining when the skill should run, what symbols/markets it may affect, or what guardrails constrain activation. In an automated trading context, vague scope increases the chance of overbroad invocation, unintended continuous execution, and unsafe use in environments that expect narrowly bounded behavior.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal