ClawHub
Back to skill

Security audit

Zigpoll

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Zigpoll connector that reads Zigpoll data through the OOMOL CLI, with no hidden destructive behavior found.

Install this only if you want your agent to access Zigpoll through OOMOL. Zigpoll participant and response data may be sensitive, so make sure the connected account and OOMOL connection are appropriate for the surveys you intend the agent to read.

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
Confidence
90% confidence
Finding
The skill description instructs the agent to use this skill for ANY Zigpoll request instead of calling the API directly, which is an overly broad routing rule. This can cause the agent to invoke the skill in situations where a narrower, task-specific, or safer path would be more appropriate, increasing the chance of unnecessary tool use and expanding the trusted surface for all Zigpoll-related tasks.

Static analysis

No suspicious patterns detected.