ClawHub
Back to skill

Security audit

Polymarket Cybersecurity Trader

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Polymarket trading skill that defaults to paper trading and only uses live trading when explicitly run with the live flag.

Install only if you are comfortable giving this skill a Simmer trading credential. Start in paper mode, keep live limits low, and note that the documented minimum-volume filter does not appear to be enforced by the code.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill references environment-backed credentials (`SIMMER_API_KEY`) and trading authority, but the markdown indicates no declared permissions while still exposing capability expectations around env access. In agent platforms that rely on declared permissions for policy enforcement and user consent, this mismatch can enable broader-than-expected secret access or cause the skill to run with sensitive credentials without an explicit capability declaration.

Vague Triggers

Medium
Confidence
76% confidence
Finding
The skill description says it 'handles all the plumbing' and broadly describes trading and execution behavior without a clear invocation boundary. In markdown- or manifest-driven agent systems, ambiguous activation criteria can cause the skill to be selected in overly broad contexts, increasing the chance of unintended market actions or credentialed execution when a user only asked for analysis or information.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.