ClawHub
Back to skill

Security audit

Web Research Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a simple web research guidance skill with no code, persistence, credential handling, or hidden behavior.

Install this as a general-purpose research helper. Treat it like any web-search workflow: do not include sensitive personal, credential, or confidential business details unless you are comfortable using them to guide research, and review cited sources before relying on conclusions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill can be invoked for essentially any research request without defined boundaries, which increases the chance it will be used in sensitive or risky contexts without additional safeguards. In practice, broad activation can lead to unintended collection of external content, handling of regulated topics, or use in contexts where users are not clearly informed about web access behavior.

Missing User Warnings

Low
Confidence
86% confidence
Finding
The skill describes collecting information from multiple sources and providing URLs, but it does not warn users that external web access and URL handling will occur. This reduces transparency and can surprise users who may not expect network activity, third-party content retrieval, or inclusion of external links in outputs.

Static analysis

No suspicious patterns detected.