ClawHub
Back to skill

Security audit

Polymarket Scout — Hourly Edge Detector

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent read-only Polymarket scanning skill, though users should treat its betting recommendations and bet sizing as risky advice.

Install only if you want an agent to fetch live Polymarket data and produce betting-oriented market signals. Treat the edge estimates, win-rate claim, and Kelly sizing as unverified gambling/financial guidance, and require explicit user confirmation before acting on any recommendation outside the skill.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The usage examples include broad natural-language trigger phrases like 'find best Polymarket bet right now,' which are likely to overlap with ordinary user requests and can cause the skill to activate when not explicitly intended. Because this skill fetches live market data and produces betting-oriented recommendations, unintended invocation could lead to inappropriate financial guidance, unnecessary external API access, or the skill being selected in contexts where a narrower tool should have been used.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.