ClawHub
Back to skill

Security audit

Web Research

Security checks for vulnerabilities and agentic risk

Overview

This is a simple web-research instruction skill with disclosed search guidance and no hidden code, persistence, or sensitive local access.

Install this if you want an agent to perform structured web research with source checking. Be aware that it may trigger on broad feasibility-verification requests and may prefer Chinese-language sources unless the user asks otherwise.

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
90% confidence
Finding
The trigger conditions are broad enough to match many normal requests involving searching, fact-finding, or feasibility checks, which can cause the skill to activate unexpectedly. Unintended activation can override more specific workflows, create unnecessary web access, and expand the agent's behavior beyond what the user explicitly asked for.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
Defaulting to Chinese resources without user opt-in introduces a locale and language bias that may return less relevant, less understandable, or policy-misaligned sources for many users. This can degrade result quality and trustworthiness, especially when the user's language, jurisdiction, or compliance context is different.

Static analysis

No suspicious patterns detected.