ClawHub
Back to skill

Security audit

Polymarket FastScaler

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed automated Polymarket trading skill, but it needs Review because it can place real trades while its documentation overstates validation in one place and the code can be configured beyond the stated BTC 5-minute scope.

Install only if you understand it can automate real-money Polymarket trades. Treat the strategy as unvalidated despite the one conflicting phrase, run paper mode first, keep tight budget caps, and do not use live cron or non-BTC/5m settings unless you have independently validated them. Protect the Simmer API key and wallet credentials.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill documentation instructs users to install and run local Python code, export API keys, use cron, and contact external services, which implies environment, filesystem, and network access, yet no permissions are declared. This is dangerous because operators and policy layers cannot accurately assess or constrain the skill's runtime capabilities, increasing the chance of over-trusting code that can access secrets, modify files, or make outbound requests.

Intent-Code Divergence

Medium
Confidence
96% confidence
Finding
The 'When to Use This Skill' section says the user may want a 'validated magnitude filter' even though the rest of the document repeatedly states the prior backtest was retracted and there is no validated edge. This contradiction can mislead users into deploying or funding a real-money trading strategy under false assumptions of validation, which is especially risky in a live trading context.

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The skill manifest describes a BTC 5-minute fast-market strategy, but the code exposes configurable asset and window parameters and even includes symbol mappings for ETH and SOL. In a live trading context, this capability drift is dangerous because users or automation may run the strategy on unvalidated assets/windows, bypassing the safety expectations set by the metadata and increasing risk of unintended or loss-making trades.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill presents conflicting quality and safety claims by advertising a 'validated magnitude filter' while simultaneously disclaiming any validated edge and retracting the original performance evidence. In a financial trading skill, this inconsistency materially increases the risk of user deception, inappropriate trust, and real monetary loss from live use.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.