ClawHub
Back to skill

Security audit

SQL查询工具(免费版)

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent SQL command-line helper, but it gives agents broad database read, write, import, export, reset, and delete authority without strong user-confirmation or production-safety guardrails.

Install only if you are comfortable with an agent using command-line database clients. Treat it as needing explicit human approval for any UPDATE, DELETE, INSERT, reset, import, export, production connection, or credential-backed operation, and prefer read-only accounts where possible.

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
92% confidence
Finding
The activation guidance is broad enough to trigger the skill for generic 'database operations' and 'data storage management' tasks, even though the skill exposes exec/write capabilities and supports modifying data. In an agent setting, ambiguous routing can cause the skill to be selected for sensitive tasks without explicit user intent, increasing the chance of unintended database access or destructive actions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises create/query/export, modify/reset/import, and save/convert operations but does not prominently warn that these actions can overwrite data, alter state, or leak sensitive records through export. In combination with exec and write tool access, this creates a realistic risk of accidental destructive changes or unauthorized data exfiltration when an agent follows the skill automatically.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.