ClawHub
Back to skill

Security audit

Zenscrape

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Zenscrape connector wrapper for fetching public URLs through OOMOL, with no hidden persistence or destructive behavior found.

Before installing, confirm you are comfortable using OOMOL's oo CLI and connected Zenscrape account to fetch public URLs. Avoid using it for sensitive or private URLs unless you are willing for the target URL and request details to pass through the connector service.

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
94% confidence
Finding
The trigger guidance is excessively broad: 'Use this skill for ANY Zenscrape request' and 'Whenever a task involves Zenscrape' can cause the agent to invoke this skill in loosely related contexts without adequate narrowing or user intent checks. Because the skill can fetch arbitrary public URLs via a connector, over-triggering increases the chance of unnecessary external requests, privacy leakage through queried URLs, or bypass of more appropriate task-specific handling.

Static analysis

No suspicious patterns detected.