ClawHub
Back to skill

Security audit

Agentql

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AgentQL web scraping guide, but users should avoid using it on sensitive pages unless they are comfortable with AgentQL processing that page data.

Install only if you intend to use AgentQL for scraping or browser automation. Do not run it against sensitive, internal, regulated, or authenticated pages unless you have reviewed AgentQL's data handling and are comfortable with page content or extracted data being processed by that service.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs users to configure an AgentQL API key and send natural-language queries against webpages, but it does not clearly warn that webpage content, automation context, and extracted data may be transmitted to a third-party service. This can cause unintentional disclosure of sensitive page data or browsing targets, especially when users apply the skill to internal, authenticated, or proprietary websites.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.