ClawHub
Back to skill

Security audit

web-browsing

Security checks for vulnerabilities and agentic risk

Overview

This is a simple instruction-only web browsing skill with some broad activation wording, but no hidden code, persistence, credential handling, or destructive behavior.

Before installing, note that this skill may activate for broad web or content-related prompts. It is best suited for explicit requests to visit a URL, search online, summarize a webpage, or extract webpage data.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger keywords are extremely broad (for example, 'web', 'content', 'browse', and 'extract'), which can cause the skill to activate for many unrelated user requests. In an agent setting, over-broad activation increases the chance that this skill intercepts prompts unnecessarily and influences behavior outside its intended scope, especially because it suggests web access and possible command execution capability.

Vague Triggers

Low
Confidence
86% confidence
Finding
The activation guidance lists broad 'use when' examples but does not define meaningful boundaries for when the skill must not activate. This ambiguity can lead to over-selection of the skill for generic information requests, increasing unintended tool use and raising the risk of unnecessary browsing or content fetching.

Static analysis

No suspicious patterns detected.