ClawHub
Back to skill

Security audit

Poly Tradebot

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent news-to-prediction-market analysis workflow, with disclosed file output and no evidence of hidden execution, credential access, trading actions, or exfiltration.

Before installing, understand that the skill may save market-analysis outputs in memory/ and may reuse those files later to regenerate tables. Treat its Polymarket recommendations as analysis, not financial advice, and review or delete saved memory files if the URLs, prompts, or conclusions are sensitive.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly writes per-article analyses and a summary table into the shared memory/ directory, but the description does not warn users about this persistence behavior. Hidden persistence can expose sensitive prompts, URLs, market analysis, or derived recommendations to later runs or other skills, creating avoidable data-retention and context-leakage risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.