ClawHub
Back to skill

Security audit

Website Monitor

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward website checker that fetches user-supplied URLs and shows no hidden persistence or destructive behavior.

Install this if you want a simple URL uptime checker. Be aware it will make outbound requests to the URLs you provide and read response bodies to compute hashes or check text, so use care with private or internal URLs.

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
  • 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
93% confidence
Finding
The skill advertises network-capable behavior but does not declare any explicit tool scope or permissions boundary. That creates a transparency and governance gap: the agent may be invoked for network activity without clear least-privilege controls or reviewer-visible authorization metadata.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases are broad and map closely to common user requests, which increases the chance this skill auto-activates in situations where the user did not specifically intend to run a network-checking utility. Because the skill performs outbound URL fetches, overbroad activation can lead to unexpected network access, user confusion, or misuse in broader contexts than intended.

Static analysis

No suspicious patterns detected.